© 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. 23847
    Prev
    Next
    INDEX
    Explanations

    coastal

    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
    mie
    -0.28
    mars
    -0.25
    EFR
    -0.25
    redi
    -0.25
    _common
    -0.25
     curtains
    -0.24
    oun
    -0.24
    æĹłæīĢè°ĵ
    -0.24
    寻常
    -0.24
    éĶŁ
    -0.24
    POSITIVE LOGITS
    hoot
    0.28
    aveled
    0.25
    ä¸įèĪį
    0.25
     elsif
    0.25
    /native
    0.24
    felt
    0.24
     branch
    0.24
    lew
    0.24
    趣
    0.24
    reuse
    0.23
    Activations Density 0.374%

    No Known Activations