© 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. 25-TRANSCODER-HP
    7. 108132
    Prev
    Next
    INDEX
    Explanations

    transform

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resco
    -0.27
    quee
    -0.26
    lify
    -0.23
     res
    -0.23
     Dav
    -0.23
    åıijå±ķçļĦ
    -0.23
    ->↵
    -0.23
    å½ĵãģŁãĤĬåīį
    -0.23
    '{
    -0.22
    othy
    -0.22
    POSITIVE LOGITS
    ingen
    0.26
     township
    0.25
    åħ¨æĹ¥
    0.24
    èĤĩ
    0.23
    }}}
    0.23
    rts
    0.23
    ä¸Ģæīĭ
    0.23
    bens
    0.23
    VRT
    0.23
    èĬĤ缮
    0.22
    Activations Density 0.440%

    No Known Activations