© 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. 9898
    Prev
    Next
    INDEX
    Explanations

    Formal documents, code

    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
    utos
    -0.26
     redes
    -0.25
    èĸľ
    -0.25
     watt
    -0.25
     loose
    -0.25
    lers
    -0.24
    RuleContext
    -0.24
    ADOW
    -0.24
    CKET
    -0.24
     plotting
    -0.24
    POSITIVE LOGITS
     Marino
    0.29
    pers
    0.27
     Monaco
    0.26
    thood
    0.26
    Persist
    0.26
     initData
    0.26
    缴éĶĢ
    0.25
    æķĻ
    0.25
    rink
    0.24
    .compat
    0.24
    Activations Density 0.000%

    No Known Activations