© 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. 22908
    Prev
    Next
    INDEX
    Explanations

    aths

    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
    set
    -0.28
    Pair
    -0.27
     aim
    -0.27
    String
    -0.26
     set
    -0.26
    (-
    -0.25
     (-
    -0.24
    .webkit
    -0.24
    si
    -0.24
    sw
    -0.24
    POSITIVE LOGITS
    rouw
    0.28
    责任åĪ¶
    0.26
    -options
    0.26
    á»Ī
    0.25
     innocence
    0.25
    éĻ¤å¤ķ
    0.25
    noon
    0.24
    çļĦåķĨåĵģ
    0.24
    gere
    0.24
    emble
    0.24
    Activations Density 0.000%

    No Known Activations