© 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. 10006
    Prev
    Next
    INDEX
    Explanations

    such as

    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¿©
    -0.09
    arf
    -0.09
    endum
    -0.08
    uve
    -0.08
     zwar
    -0.08
    åĩłä¹İæīĢæľī
    -0.08
    è°ĥ度
    -0.08
    owed
    -0.08
    ////↵
    -0.08
    chl
    -0.08
    POSITIVE LOGITS
     обÑĢазом
    0.13
    æĥħåĨµä¸ĭ
    0.11
    ä½Ĩä¸įéĻIJäºİ
    0.11
     ado
    0.10
    itecture
    0.10
    itra
    0.10
    inite
    0.09
    ness
    0.09
    .Pixel
    0.09
    onymous
    0.09
    Activations Density 0.101%

    No Known Activations