© 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. 35-TRANSCODER-HP
    7. 39795
    Prev
    Next
    INDEX
    Explanations

    sh

    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
    ONA
    -0.28
    inges
    -0.28
    INGS
    -0.28
    Į¨
    -0.27
    accordion
    -0.27
    综
    -0.26
     Pods
    -0.26
    ories
    -0.26
    egrate
    -0.26
    isons
    -0.26
    POSITIVE LOGITS
    åĴ±ä»¬
    0.28
    boo
    0.27
    un
    0.27
     impover
    0.26
    bol
    0.26
    more
    0.25
     richer
    0.24
    çļĦ帮åĬ©
    0.24
    æĽ´å¤ļ
    0.24
    .baidu
    0.23
    Activations Density 2.329%

    No Known Activations