© 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. 42795
    Prev
    Next
    INDEX
    Explanations

    Digital

    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
    tes
    -0.27
    eturn
    -0.26
    ATHER
    -0.25
     rem
    -0.25
    nite
    -0.25
     human
    -0.24
    UMAN
    -0.24
     transplant
    -0.24
     regress
    -0.24
     transf
    -0.23
    POSITIVE LOGITS
    Υ
    0.30
    äºĶå®ĺ
    0.29
    <ll
    0.28
    æĸ°éĹ»åıijå¸ĥ
    0.27
     Online
    0.26
    è´¢
    0.26
    acket
    0.25
    ctrine
    0.25
    ervlet
    0.25
    kins
    0.25
    Activations Density 0.006%

    No Known Activations