© 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. 18327
    Prev
    Next
    INDEX
    Explanations

    go/come

    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
     artifacts
    -0.35
     artifact
    -0.30
     Artifact
    -0.30
    æĦıåij³çĿĢ
    -0.29
    Means
    -0.29
     Means
    -0.28
     means
    -0.28
    edu
    -0.26
     arte
    -0.26
     possess
    -0.26
    POSITIVE LOGITS
     shoot
    0.28
    ito
    0.27
     Listed
    0.26
    FOUNDATION
    0.26
    (exc
    0.25
    çīĻ
    0.25
    itos
    0.25
     hail
    0.25
    butt
    0.25
     Fon
    0.24
    Activations Density 1.120%

    No Known Activations