© 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. 18453
    Prev
    Next
    INDEX
    Explanations

    games and competitions

    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
     score
    -1.52
     scores
    -1.43
    score
    -1.41
     Score
    -1.40
    Score
    -1.35
     scoring
    -1.33
    -score
    -1.31
     scored
    -1.29
    å¾ĹåĪĨ
    -1.27
     Scores
    -1.26
    POSITIVE LOGITS
    оваÑĢ
    0.24
    溢
    0.23
    uem
    0.23
    _soup
    0.23
    itti
    0.23
    tone
    0.23
    ichen
    0.23
    çĸ
    0.22
    latex
    0.22
    çIJĨ工大åѦ
    0.22
    Activations Density 4.214%

    No Known Activations