© 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. 30-TRANSCODER-HP
    7. 96729
    Prev
    Next
    INDEX
    Explanations

    gr

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antino
    -0.29
     teng
    -0.28
     Starter
    -0.28
    enze
    -0.27
    xfa
    -0.27
     starter
    -0.26
     Bride
    -0.26
     entityId
    -0.26
    <AM
    -0.26
    å¸ľ
    -0.26
    POSITIVE LOGITS
    Cond
    0.27
     Cond
    0.27
     Conf
    0.27
    reen
    0.26
     Ac
    0.26
    éªĮæĶ¶
    0.26
    çķľç¦½
    0.26
    al
    0.25
     cond
    0.25
    deps
    0.25
    Activations Density 0.883%

    No Known Activations