© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 44100
    Prev
    Next
    INDEX
    Explanations

    its

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    maint
    -0.26
    姿
    -0.25
     plugs
    -0.25
    大èĥĨ
    -0.25
    èĴ¹
    -0.25
    cit
    -0.24
     squeez
    -0.24
    ovies
    -0.24
     Slut
    -0.24
     Karn
    -0.24
    POSITIVE LOGITS
     proper
    0.35
     exact
    0.34
     natural
    0.32
     required
    0.30
     needed
    0.30
     precise
    0.29
     correct
    0.29
    proper
    0.29
     necessary
    0.28
    ftime
    0.28
    Activations Density 0.002%

    No Known Activations