© 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. 22-TRANSCODER-HP
    7. 129350
    Prev
    Next
    INDEX
    Explanations

    positive sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CLU
    -0.26
     hit
    -0.26
     pretext
    -0.25
     Brushes
    -0.25
    -role
    -0.24
    æĴ¬
    -0.24
    [,]
    -0.24
    asp
    -0.23
    ataka
    -0.23
    (Roles
    -0.23
    POSITIVE LOGITS
    prep
    0.28
    èĭĭ
    0.26
    roids
    0.25
    ivor
    0.23
    åľ¨ä¸ŃåĽ½
    0.23
     interp
    0.23
     densely
    0.23
    .getMin
    0.23
    Sdk
    0.23
    æµħ
    0.23
    Activations Density 0.009%

    No Known Activations