© 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. 27-TRANSCODER-HP
    7. 8441
    Prev
    Next
    INDEX
    Explanations

    ap

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    som
    -0.30
    ossal
    -0.28
    atoon
    -0.26
    itch
    -0.26
    é½
    -0.26
    mm
    -0.25
    ograms
    -0.25
     shut
    -0.25
     Grat
    -0.24
    richt
    -0.24
    POSITIVE LOGITS
    cro
    0.34
    ×
    0.34
    baz
    0.29
    uled
    0.28
    isque
    0.28
    éĤ¡
    0.27
    guns
    0.27
     cro
    0.27
    ADOW
    0.26
    éľĨ
    0.25
    Activations Density 0.238%

    No Known Activations