© 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. 31-TRANSCODER-HP
    7. 18869
    Prev
    Next
    INDEX
    Explanations

    Place names and locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     like
    -0.57
     Like
    -0.55
    like
    -0.52
    Like
    -0.50
    åĥı
    -0.48
     LIKE
    -0.42
    LIKE
    -0.39
    .like
    -0.38
    _like
    -0.38
    åĥıæĺ¯
    -0.34
    POSITIVE LOGITS
    çĥ¦
    0.29
    opes
    0.28
    macro
    0.27
    饶
    0.26
     macro
    0.26
    ocache
    0.26
     Superintendent
    0.26
    èį¤
    0.26
    abee
    0.25
    _sent
    0.25
    Activations Density 0.233%

    No Known Activations