© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22281
    Prev
    Next
    INDEX
    Explanations

    lobster, ster

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Basel
    -0.28
    æīī
    -0.28
    ç«ĭ
    -0.28
    信念
    -0.26
    款
    -0.25
    澡
    -0.25
     assertion
    -0.25
    rest
    -0.25
     Assert
    -0.24
    OUS
    -0.24
    POSITIVE LOGITS
    åŀĤ
    0.29
    åĤij
    0.27
    nett
    0.27
    orks
    0.27
     /*!<
    0.26
    iphy
    0.26
    æ°Ķæ°Ľ
    0.25
    ccione
    0.25
    jang
    0.25
    è¾
    0.24
    Activations Density 0.079%

    No Known Activations