© 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. 54213
    Prev
    Next
    INDEX
    Explanations

    prosthetics and aids

    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
    ounds
    -0.08
    åĪ¶åº¦
    -0.08
    AttributeValue
    -0.08
     Glow
    -0.08
    /as
    -0.08
    港
    -0.08
    çģŃ
    -0.08
    guess
    -0.08
    _NC
    -0.08
    è§ĨåIJ¬
    -0.08
    POSITIVE LOGITS
    æķĿ
    0.10
    åľ¨å®¶
    0.10
     ëį
    0.09
    佩æĪ´
    0.09
    orama
    0.09
    ç³Ĺ
    0.09
    çĶŁæ´»çļĦ
    0.08
    меÑģ
    0.08
    ç¤¾åĽ¢
    0.08
    MI
    0.08
    Activations Density 0.103%

    No Known Activations