© 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. 39168
    Prev
    Next
    INDEX
    Explanations

    separating lists or phrases

    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
    	TokenName
    -0.12
    èįĨ
    -0.10
    _rg
    -0.09
    æ¾į
    -0.09
    BOSE
    -0.08
    _regs
    -0.08
    eref
    -0.08
    åĨı
    -0.08
    éŀŃ
    -0.08
    æºī
    -0.08
    POSITIVE LOGITS
    INTERNAL
    0.08
     porr
    0.08
    æŀĦçŃij
    0.08
    ç«
    0.08
     knob
    0.08
    ç°ĩ
    0.08
     Gener
    0.07
    å¾Ĺå¤ļ
    0.07
    åªĽ
    0.07
     Pull
    0.07
    Activations Density 0.062%

    No Known Activations