© 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. 58141
    Prev
    Next
    INDEX
    Explanations

    axle, wheel, suspension, seat

    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
    /jav
    -0.10
    è¿İæİ¥
    -0.10
    åŁķ
    -0.10
    è¿İ
    -0.10
    /xhtml
    -0.10
    á»ĥn
    -0.09
    éĢŁåº¦å¿«
    -0.09
    rawid
    -0.09
    _REDIRECT
    -0.09
    éĻª
    -0.09
    POSITIVE LOGITS
    6
    0.08
    å±Ģéĥ¨
    0.08
    1
    0.08
    ä¸Ģ人
    0.08
    8
    0.08
    0
    0.08
    pon
    0.08
    æŀ¶æŀĦ
    0.08
    2
    0.08
    5
    0.08
    Activations Density 0.062%

    No Known Activations