© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10509
    Prev
    Next
    INDEX
    Explanations

    collections of essays and stories

    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
    ä¸ĩåįĥ
    -0.09
     lòng
    -0.08
    .bo
    -0.08
     thousands
    -0.08
    otor
    -0.08
     millions
    -0.08
    dale
    -0.08
    ä¼ĺè¶Ĭ
    -0.07
    _bindings
    -0.07
    ENDOR
    -0.07
    POSITIVE LOGITS
    æĻ¯çĤ¹
    0.11
    åħĪ导
    0.10
    åħ¥éĢī
    0.10
    çĿĢçľ¼äºİ
    0.10
    äºİä¸Ģä½ĵ
    0.10
    è´£ç¼ĸ
    0.10
    çŁŃ
    0.10
    ç²Ĺ
    0.10
    ä¸ŃåĽ½ä¼ģä¸ļ
    0.09
    éĢīåıĸ
    0.09
    Activations Density 0.100%

    No Known Activations