© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 41110
    Prev
    Next
    INDEX
    Explanations

    Health studies/statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Produce
    -0.26
    ಥ
    -0.25
    åİŁæłĩé¢ĺ
    -0.25
    oyo
    -0.25
    IQUE
    -0.24
    -that
    -0.24
    ÑĤив
    -0.24
    ijn
    -0.24
    éĤ£ä¹Īç®Ģåįķ
    -0.24
     THAT
    -0.23
    POSITIVE LOGITS
     is
    0.52
    ——
    0.45
     —
    0.43
    —is
    0.41
     was
    0.40
    —
    0.40
    —a
    0.40
    —an
    0.37
    0.36
    ————
    0.35
    Activations Density 0.006%

    No Known Activations