© 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. 23543
    Prev
    Next
    INDEX
    Explanations

    abs

    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
     walkthrough
    -0.30
    ospace
    -0.28
    å¢ĻéĿ¢
    -0.26
    è¿Ľè¡Įåħ¨éĿ¢
    -0.26
    山顶
    -0.26
    quota
    -0.24
     vibes
    -0.24
    éĢĥ
    -0.24
    PAT
    -0.24
     snow
    -0.24
    POSITIVE LOGITS
    imed
    0.30
     Duncan
    0.27
    享
    0.26
    ichern
    0.26
    amed
    0.25
    ny
    0.25
    ÃŃm
    0.25
    cient
    0.24
    odyn
    0.24
    imations
    0.24
    Activations Density 0.001%

    No Known Activations