© 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. 18836
    Prev
    Next
    INDEX
    Explanations

    drinking

    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
     consumption
    -0.36
    æ¶Īè´¹
    -0.35
     Consumption
    -0.35
    æ¶ĪèĢĹ
    -0.32
    consum
    -0.32
     consum
    -0.32
    æ¶Īè²»
    -0.31
     Consum
    -0.31
     consuming
    -0.30
     consumo
    -0.30
    POSITIVE LOGITS
     heavily
    0.35
     timber
    0.29
     sent
    0.29
    è½»
    0.28
    çĭĤ
    0.28
    ugo
    0.26
    _sent
    0.26
     within
    0.26
     inside
    0.26
     behind
    0.26
    Activations Density 1.002%

    No Known Activations