© 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. 18-TRANSCODER-HP
    7. 89192
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJ¦
    -0.27
    getBody
    -0.26
    (body
    -0.26
    æľīåĩłä¸ª
    -0.26
    izo
    -0.25
    gnore
    -0.25
    é¢ĩæľī
    -0.24
     hÆ°á»Łng
    -0.24
    ocz
    -0.24
    "—
    -0.24
    POSITIVE LOGITS
    æł¡
    0.30
     admissions
    0.28
     testimonials
    0.27
    jian
    0.25
     Hak
    0.25
     cri
    0.25
    ä½ĵ系建设
    0.25
    ç´¢èµĶ
    0.24
    leshooting
    0.24
    åŁİå¸Ĥ建设
    0.24
    Activations Density 4.935%

    No Known Activations

    This feature has no known activations.