© 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. 107956
    Prev
    Next
    INDEX
    Explanations

    Lanc

    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
     tools
    -0.26
    /themes
    -0.25
    (reverse
    -0.25
    æ·±åħ¥
    -0.24
     tearDown
    -0.24
     irreversible
    -0.24
    éļħ
    -0.23
    Äĥn
    -0.23
    å·¥åħ·
    -0.23
    _NS
    -0.23
    POSITIVE LOGITS
    ument
    0.32
    busters
    0.31
    èįŁ
    0.29
    ewolf
    0.26
    sters
    0.26
    çIJĨ工大åѦ
    0.25
    _term
    0.25
    ucc
    0.24
     META
    0.24
     NODE
    0.24
    Activations Density 0.117%

    No Known Activations