© 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. 55815
    Prev
    Next
    INDEX
    Explanations

    synaptic mechanisms, activities, plasticity, integration

    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
    çĽĶ
    -0.10
    ra
    -0.10
    _SUITE
    -0.09
    å±¥è¡Į
    -0.09
    çĻ½é¢Ĩ
    -0.09
    alist
    -0.09
    rai
    -0.09
    _TUN
    -0.09
    lias
    -0.09
    æĿŃå·ŀå¸Ĥ
    -0.09
    POSITIVE LOGITS
    éĻ©
    0.09
    ysi
    0.09
    glyph
    0.08
    åĩłå¼ł
    0.08
    ahoo
    0.08
    çĶ³è¯ī
    0.08
     unab
    0.07
     Pon
    0.07
    nodeName
    0.07
    ilty
    0.07
    Activations Density 0.002%

    No Known Activations