© 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. 19074
    Prev
    Next
    INDEX
    Explanations

    man-related

    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
    auss
    -0.27
    .writ
    -0.26
     Missile
    -0.26
    éľĨ
    -0.26
     tá»
    -0.26
     isa
    -0.25
     Gauss
    -0.24
    "She
    -0.24
    lete
    -0.24
    emory
    -0.24
    POSITIVE LOGITS
     man
    0.31
     manh
    0.29
     closed
    0.28
    éĹŃ
    0.27
    æµģ
    0.26
    å°ģéĹŃ
    0.26
     CLOSED
    0.26
    compact
    0.25
    oman
    0.25
    man
    0.25
    Activations Density 2.282%

    No Known Activations