© 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. 36499
    Prev
    Next
    INDEX
    Explanations

    loan, visitors, fellow, gap year, appointment

    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
    uele
    -0.10
    çĭł
    -0.08
    nds
    -0.08
    è®Ńç»ĥ
    -0.08
    è¿ĻäºĽéĥ½æĺ¯
    -0.08
     Gda
    -0.08
    èĥŃ
    -0.08
    rose
    -0.08
    管线
    -0.08
    _FAR
    -0.08
    POSITIVE LOGITS
    æľŁéĹ´
    0.10
    (Optional
    0.09
    æĸ¹ä¾¿
    0.09
    对æĸ¹
    0.09
    æľŁéĸĵ
    0.08
    座
    0.08
    å¤Ļ
    0.08
    饱
    0.08
    .tmp
    0.08
    Multiplier
    0.08
    Activations Density 0.169%

    No Known Activations