© 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. 33-TRANSCODER-HP
    7. 54527
    Prev
    Next
    INDEX
    Explanations

    yet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     already
    -0.36
     still
    -0.35
     nevertheless
    -0.33
    already
    -0.33
     yet
    -0.33
    ä»į
    -0.32
    still
    -0.32
    _already
    -0.32
    yet
    -0.32
     now
    -0.30
    POSITIVE LOGITS
    -produced
    0.27
     amount
    0.27
    amount
    0.27
    Amount
    0.26
     spr
    0.25
     ast
    0.25
     Amount
    0.25
    èĢĥå¯Ł
    0.25
     reck
    0.25
     counted
    0.24
    Activations Density 0.041%

    No Known Activations