© 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. 89557
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    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
     popular
    -0.30
     lit
    -0.29
    å±ħ
    -0.29
     v
    -0.29
    ç²¾åĵģ
    -0.28
    Defaults
    -0.28
     gl
    -0.28
    Popular
    -0.27
    羣çļĦæĺ¯
    -0.27
    tr
    -0.26
    POSITIVE LOGITS
    ohana
    0.28
    _mgmt
    0.26
    roleum
    0.26
    .jsx
    0.26
     %↵↵
    0.25
    身ä½ĵåģ¥åº·
    0.25
    /stretch
    0.25
     cio
    0.25
    eton
    0.25
    身å¿ĥåģ¥åº·
    0.24
    Activations Density 11.272%

    No Known Activations