© 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. 43607
    Prev
    Next
    INDEX
    Explanations

    Mus

    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
    irie
    -0.28
    yre
    -0.27
    æĹ¢çĦ¶
    -0.27
    ä¾Ŀ
    -0.26
     Fay
    -0.25
    icha
    -0.25
    icont
    -0.25
    æĬĹæĪĺ
    -0.25
    ayas
    -0.25
    airo
    -0.25
    POSITIVE LOGITS
     dv
    0.28
    ovich
    0.27
    åĭº
    0.26
    ottie
    0.26
    çİĭåŃIJ
    0.26
    oscope
    0.24
    æ¼ī
    0.24
    zza
    0.24
    -du
    0.24
    è¯Ľ
    0.23
    Activations Density 0.001%

    No Known Activations