© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 98168
    Prev
    Next
    INDEX
    Explanations

    already

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĩłä¸ª
    -0.35
    å¤ļ个
    -0.35
     several
    -0.34
     multiple
    -0.33
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.32
    multiple
    -0.30
    æ²ī
    -0.29
     many
    -0.29
    许å¤ļ
    -0.29
    å¹¾åĢĭ
    -0.28
    POSITIVE LOGITS
     evidence
    0.24
    зе
    0.24
     acum
    0.23
    anic
    0.23
     PTS
    0.23
    æĥ®
    0.23
    .EventHandler
    0.23
     ---------------------------------------------------------------------------↵
    0.23
    actic
    0.23
     Dot
    0.23
    Activations Density 0.005%

    No Known Activations