© 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. 12-TRANSCODER-HP
    7. 23086
    Prev
    Next
    INDEX
    Explanations

    point

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cond
    -0.32
    cond
    -0.28
     raised
    -0.27
     Cond
    -0.27
    -cond
    -0.26
    Cond
    -0.26
    _raise
    -0.25
    æĵį
    -0.25
    (cond
    -0.24
    isty
    -0.24
    POSITIVE LOGITS
    xhr
    0.27
    EXTERN
    0.26
    éħĴç²¾
    0.26
    fell
    0.26
    BCM
    0.26
    /navigation
    0.25
     individually
    0.25
    éĺĦ
    0.25
    æĻºèĥ½æīĭæľº
    0.25
    .getSimpleName
    0.25
    Activations Density 0.012%

    No Known Activations