© 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. 22524
    Prev
    Next
    INDEX
    Explanations

    Chairs and seats

    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
     largest
    -0.28
     widest
    -0.28
     greatest
    -0.27
    çĻ¾å®¶
    -0.26
    sealed
    -0.26
     Gift
    -0.26
    å¼Ĥ
    -0.26
    èµī
    -0.26
     doubled
    -0.25
    å¼ĤæĢ§
    -0.25
    POSITIVE LOGITS
    former
    0.27
    pike
    0.25
    (forms
    0.25
    uliar
    0.25
    ATOR
    0.25
    <Character
    0.25
    MSN
    0.25
    ator
    0.24
    amac
    0.24
    ÑĥеÑĤ
    0.24
    Activations Density 0.003%

    No Known Activations