© 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. 27-TRANSCODER-HP
    7. 8165
    Prev
    Next
    INDEX
    Explanations

    suicide

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ella
    -0.31
    ç§ĭ
    -0.28
     static
    -0.28
    è¡ĢèĦĤ
    -0.27
     fing
    -0.26
     Static
    -0.26
    责任
    -0.26
    static
    -0.26
    .Private
    -0.25
     private
    -0.25
    POSITIVE LOGITS
    /respond
    0.26
    ][-
    0.25
    Haz
    0.25
     neighb
    0.24
    åĽ´çĿĢ
    0.24
    åħ¶å®ĥéĹ®é¢ĺ
    0.24
    VRT
    0.24
    PageRoute
    0.24
    VRTX
    0.24
    wy
    0.24
    Activations Density 0.006%

    No Known Activations