© 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. 42637
    Prev
    Next
    INDEX
    Explanations

    icus

    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
    溲
    -0.28
    lew
    -0.28
    nees
    -0.28
    év
    -0.27
     Nude
    -0.26
     impr
    -0.26
    ines
    -0.26
    eced
    -0.25
    ÑĥÑģÑĤÑĢой
    -0.25
    (suite
    -0.25
    POSITIVE LOGITS
    æĬĵ
    0.29
    ĥģ
    0.28
    æ£ļ
    0.26
    对çħ§
    0.26
    æ´ŀ
    0.25
    amps
    0.25
    etty
    0.25
    à¸ļาล
    0.25
    clang
    0.25
    Languages
    0.25
    Activations Density 0.001%

    No Known Activations