© 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. 32-TRANSCODER-HP
    7. 43020
    Prev
    Next
    INDEX
    Explanations

    scientific measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pl
    -0.29
    ue
    -0.29
    èĬľ
    -0.28
     fscanf
    -0.27
    çĻ½çĻ½
    -0.27
    pl
    -0.27
    ä¸ij
    -0.26
     Rule
    -0.25
     NOM
    -0.25
    俯
    -0.25
    POSITIVE LOGITS
    -inc
    0.26
    enser
    0.26
    çĵľ
    0.26
    brace
    0.26
    wich
    0.26
    bro
    0.26
     segreg
    0.25
    ¢åįķ
    0.25
    idelberg
    0.24
    outdir
    0.24
    Activations Density 0.001%

    No Known Activations