© 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. 54642
    Prev
    Next
    INDEX
    Explanations

    of

    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
    欲
    -0.27
    اÙģت
    -0.25
    çľģåħ¬å®īåİħ
    -0.25
    zig
    -0.25
     Register
    -0.25
    Register
    -0.24
    UTES
    -0.24
    Camp
    -0.24
    Closure
    -0.23
    brig
    -0.23
    POSITIVE LOGITS
    icit
    0.31
    .hist
    0.30
     Serialized
    0.29
    ussen
    0.28
    icated
    0.28
    /generated
    0.28
     OnDestroy
    0.27
    minated
    0.26
     Hist
    0.26
     bestowed
    0.26
    Activations Density 0.006%

    No Known Activations