© 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. 35-TRANSCODER-HP
    7. 38881
    Prev
    Next
    INDEX
    Explanations

    say ":"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     likewise
    -0.28
     unless
    -0.28
     via
    -0.28
     maybe
    -0.27
     since
    -0.27
     accordingly
    -0.27
     as
    -0.26
     onto
    -0.26
     finally
    -0.26
     contains
    -0.25
    POSITIVE LOGITS
    :
    0.50
    0
    0.46
    2
    0.40
    :+
    0.39
    1
    0.39
    3
    0.38
    :auto
    0.36
    :t
    0.36
    7
    0.35
    :/
    0.35
    Activations Density 4.429%

    No Known Activations