© 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. 48221
    Prev
    Next
    INDEX
    Explanations

    Joshua 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
    侧ç»ĵæŀĦæĢ§
    -0.11
    ãģĵãģ¨
    -0.11
    éĻī
    -0.11
    аÑĤоÑĢ
    -0.11
    rement
    -0.10
    ÙĬÙĤ
    -0.10
    gers
    -0.10
    edList
    -0.10
    ç¾¤å²Ľ
    -0.10
    ainen
    -0.10
    POSITIVE LOGITS
    ../../../
    0.14
    á»ĩt
    0.11
    ision
    0.11
    lish
    0.10
    åŃIJéĩĮ
    0.09
    ly
    0.09
    ระ
    0.09
    çĦ¶
    0.09
    __('
    0.08
    lings
    0.08
    Activations Density 0.265%

    No Known Activations