© 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. 33-TRANSCODER-HP
    7. 54811
    Prev
    Next
    INDEX
    Explanations

    We

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     happens
    -0.30
    éķ¿
    -0.27
     long
    -0.26
     happen
    -0.26
     CLK
    -0.25
    ASF
    -0.25
     happened
    -0.24
    ä¸ĢéĿ¢
    -0.24
     electronically
    -0.24
    çķĻ
    -0.24
    POSITIVE LOGITS
    outh
    0.32
    itr
    0.29
    ible
    0.27
    å®ŀ
    0.27
    ׳×ķת
    0.26
    quent
    0.26
    itness
    0.25
    ТÐIJ
    0.25
     Dense
    0.25
    ioc
    0.25
    Activations Density 0.010%

    No Known Activations