© 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. 4611
    Prev
    Next
    INDEX
    Explanations

    Asheville

    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
    渤海
    -0.11
    hausen
    -0.09
    ä¸Ńå¤ĸ
    -0.09
    بÙĬÙĨ
    -0.09
    çŁ³æ²¹
    -0.08
    èĦĬ
    -0.08
    åĬłæ²¹
    -0.08
    ric
    -0.08
    èħ°éĥ¨
    -0.08
    鲸
    -0.08
    POSITIVE LOGITS
    ç¿ł
    0.10
    çŃĩ
    0.10
    çĻ½äºij
    0.10
    çİ»
    0.10
     extrem
    0.10
     ngại
    0.09
    èĸ®
    0.09
     بط
    0.09
     tang
    0.09
    çĦļ
    0.09
    Activations Density 0.084%

    No Known Activations