© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31027
    Prev
    Next
    INDEX
    Explanations

    argonauts, argus, arges, argenta, argonne

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thiá»ĥu
    -0.11
    kaar
    -0.10
    tras
    -0.10
    istic
    -0.10
    ahoo
    -0.09
    enen
    -0.09
    ikki
    -0.09
    idad
    -0.09
    eker
    -0.09
    ning
    -0.09
    POSITIVE LOGITS
    UMENT
    0.13
    itecture
    0.12
    onaut
    0.12
    inals
    0.12
    entina
    0.11
    ä¸įæ¸ħ
    0.10
    entine
    0.10
    ueil
    0.10
    åī¯ç§ĺ书éķ¿
    0.10
    t
    0.09
    Activations Density 0.061%

    No Known Activations