© 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. 57842
    Prev
    Next
    INDEX
    Explanations

    Blogger

    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
    ump
    -0.09
    æ··
    -0.08
    AGIC
    -0.08
    åĴķ
    -0.08
    _website
    -0.08
    aoke
    -0.08
    adoo
    -0.08
    æ¡ĤèĬ±
    -0.08
     =~
    -0.08
    çݳ
    -0.08
    POSITIVE LOGITS
    ower
    0.08
    atter
    0.08
    cts
    0.07
    åĬ³åĬ¨
    0.07
    Mahon
    0.07
    æ¦ľ
    0.07
    å°ıåŀĭ
    0.07
    空çĻ½
    0.07
    躺
    0.07
    owing
    0.07
    Activations Density 0.060%

    No Known Activations