© 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. 27-TRANSCODER-HP
    7. 56528
    Prev
    Next
    INDEX
    Explanations

    code, hex, and bitwise operations

    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
    Negative Logits
     powers
    -0.81
     power
    -0.68
    powers
    -0.65
    power
    -0.65
     Powers
    -0.64
    _power
    -0.61
    Power
    -0.60
     Power
    -0.60
    å¹Ĥ
    -0.59
    -power
    -0.58
    POSITIVE LOGITS
    stag
    0.28
    amb
    0.27
    ape
    0.26
    ESC
    0.26
    æµģæ°´
    0.26
    oller
    0.25
    anger
    0.25
    amber
    0.25
    alles
    0.24
     seg
    0.24
    Activations Density 0.017%

    No Known Activations