© 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. 98378
    Prev
    Next
    INDEX
    Explanations

    planets

    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
    zos
    -0.26
     PICK
    -0.26
     squeeze
    -0.26
     diligence
    -0.25
    ย
    -0.25
    ynes
    -0.25
    åĭ¤
    -0.25
    éĢŁ
    -0.25
    涯
    -0.24
    åĨĹ
    -0.24
    POSITIVE LOGITS
    æĦŁåħ´è¶£
    0.25
    ụ
    0.25
    agen
    0.25
    ien
    0.25
    __$
    0.24
    æ°¿
    0.23
     stump
    0.23
    âĦĴ
    0.23
    ulet
    0.23
    .setContent
    0.23
    Activations Density 0.004%

    No Known Activations