© 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. 10436
    Prev
    Next
    INDEX
    Explanations

    gray or grey

    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
    å¯Į
    -0.10
    èªĵ
    -0.09
    abei
    -0.09
    æ¯Ĵ
    -0.09
    vak
    -0.09
    รา
    -0.09
    å°¤
    -0.09
    èłĥ
    -0.09
    ismatic
    -0.09
     CONTRIBUTORS
    -0.09
    POSITIVE LOGITS
    çģ°
    0.17
    çģ°èī²
    0.16
    gray
    0.14
     grey
    0.14
     gray
    0.14
    Gray
    0.12
    grey
    0.12
    åŁºè°ĥ
    0.12
     Grey
    0.11
    (gray
    0.11
    Activations Density 0.047%

    No Known Activations