© 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. 35483
    Prev
    Next
    INDEX
    Explanations

    somatostatin or specific names

    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
    ervers
    -0.09
    ENDOR
    -0.09
    Formats
    -0.08
     Schwe
    -0.08
    å±ĭ
    -0.08
    çķĪ
    -0.08
    _HAND
    -0.08
    å¸ĥèݱ
    -0.08
    _OPER
    -0.08
    dera
    -0.08
    POSITIVE LOGITS
    éĻį
    0.11
    亩
    0.10
    éªŀ
    0.09
    oul
    0.09
    ä¹Łä¸įæķ¢
    0.09
    jiang
    0.08
    纸ä¸Ĭ
    0.08
    åĭĭ
    0.08
    acao
    0.08
    éļĶçĿĢ
    0.08
    Activations Density 0.002%

    No Known Activations