© 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. 31560
    Prev
    Next
    INDEX
    Explanations

    names and company affiliations

    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
    aed
    -0.09
    è®°å¿ĨåĬĽ
    -0.08
     Carpenter
    -0.08
    åıijå±ķä¸Ń
    -0.08
    alic
    -0.08
    à¸ľà¸ªà¸¡
    -0.07
    omal
    -0.07
    [âĢ¦]
    -0.07
    STANCE
    -0.07
    å°ıåºĹ
    -0.07
    POSITIVE LOGITS
    为åħ¶
    0.13
    çļĦä¸Ģç§į
    0.10
     sourceMapping
    0.09
    对åħ¶
    0.09
     коÑĤоÑĢого
    0.09
    对åħ¶è¿Ľè¡Į
    0.09
    /thumb
    0.09
    é£ŀèĪ¹
    0.09
    è¯ģåĪ¸äº¤æĺĵ
    0.09
    éĻ¤å¤ĸ
    0.09
    Activations Density 0.711%

    No Known Activations