© 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. 23115
    Prev
    Next
    INDEX
    Explanations

    coast

    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
    inand
    -0.27
    Band
    -0.27
    _degree
    -0.25
    æ®į
    -0.25
     ê
    -0.25
    plete
    -0.25
    .Storage
    -0.25
    mere
    -0.24
    å¾½
    -0.24
    ÅĤe
    -0.24
    POSITIVE LOGITS
    ervas
    0.29
    .pack
    0.26
    aff
    0.25
     chù
    0.25
    è´¯
    0.25
    Explicit
    0.24
    箾
    0.24
    (strict
    0.24
    -aff
    0.24
     {-
    0.23
    Activations Density 0.001%

    No Known Activations