© 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. 42173
    Prev
    Next
    INDEX
    Explanations

    read/oad

    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
    amer
    -0.30
    ATHER
    -0.29
    athers
    -0.27
     rewriting
    -0.27
    undry
    -0.26
    æ¶Īè´¹èĢħçļĦ
    -0.26
    toLocale
    -0.26
    ERIC
    -0.26
    lew
    -0.26
    athering
    -0.26
    POSITIVE LOGITS
    uate
    0.28
    ingu
    0.28
    ed
    0.27
    missible
    0.27
     organ
    0.26
    orm
    0.25
    MISS
    0.25
    um
    0.25
    opt
    0.25
    gest
    0.25
    Activations Density 0.001%

    No Known Activations