© 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. 41626
    Prev
    Next
    INDEX
    Explanations

    Microsoft

    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
    jerne
    -0.29
     google
    -0.27
    çĻ¾åº¦
    -0.27
     claim
    -0.27
    é²ľèī³
    -0.26
    æĽ´éĢĤåIJĪ
    -0.26
    ably
    -0.26
    rich
    -0.26
     themes
    -0.26
    al
    -0.26
    POSITIVE LOGITS
    bourg
    0.30
    illac
    0.30
    uild
    0.27
     MC
    0.27
     undercut
    0.25
    itational
    0.25
    åįĥéĩĮ
    0.25
    iliate
    0.25
     Ain
    0.25
    vendor
    0.24
    Activations Density 0.009%

    No Known Activations