© 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. 43906
    Prev
    Next
    INDEX
    Explanations

    Refer

    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
    åı«
    -1.09
     calls
    -0.63
     call
    -0.61
    call
    -0.59
    Call
    -0.58
     Call
    -0.57
    _call
    -0.54
    åı«åģļ
    -0.54
    (call
    -0.53
     Calls
    -0.52
    POSITIVE LOGITS
     refer
    1.34
     referred
    1.32
    refer
    1.05
     Refer
    1.04
     refers
    1.03
     referring
    1.03
     REFER
    0.99
    Refer
    0.98
    _refer
    0.88
     referencia
    0.80
    Activations Density 0.002%

    No Known Activations