© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51159
    Prev
    Next
    INDEX
    Explanations

    encoder values

    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
    phones
    -0.09
    åıĺåİĭ
    -0.09
    è¿ľæĻ¯
    -0.09
    _SI
    -0.09
    tributes
    -0.09
     Seeds
    -0.09
    abd
    -0.08
    éĩĩ访æŶ
    -0.08
    ä¸įä¸ĭ
    -0.08
    è¶Ĭéĩİ
    -0.08
    POSITIVE LOGITS
    èĻ
    0.11
    ugi
    0.09
    ali
    0.09
    åĹŁ
    0.09
    éĻ¤åİ»
    0.08
    義
    0.08
     Salv
    0.08
    anni
    0.08
    Coder
    0.08
     Dest
    0.08
    Activations Density 0.119%

    No Known Activations