© 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. 130354
    Prev
    Next
    INDEX
    Explanations

    Familiarity

    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
    æĦ¿
    -0.28
    å¨ĺ
    -0.24
    née
    -0.24
    æ°¸ä¸į
    -0.23
    (#)
    -0.23
    eva
    -0.23
    çħ
    -0.23
    LERÄ°
    -0.23
    鸣
    -0.22
    çĪ¸å¦Ī
    -0.22
    POSITIVE LOGITS
    izing
    0.29
     competing
    0.28
    ization
    0.27
     ol
    0.27
    ité
    0.26
    on
    0.26
     natural
    0.26
     background
    0.25
    ities
    0.25
     known
    0.25
    Activations Density 0.244%

    No Known Activations