© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53042
    Prev
    Next
    INDEX
    Explanations

    "per"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    pls
    -0.30
    atches
    -0.26
    pcl
    -0.25
     susceptibility
    -0.25
     UR
    -0.24
    urat
    -0.24
    .templates
    -0.23
    ur
    -0.23
    ber
    -0.23
    CKET
    -0.23
    POSITIVE LOGITS
    formed
    0.31
    妥
    0.28
    彤
    0.28
    forme
    0.28
    æĹ¥
    0.26
     rh
    0.26
    forms
    0.25
    çļĦæĹ¥
    0.25
    signed
    0.25
    .forms
    0.24
    Activations Density 0.014%

    No Known Activations