© 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. 31726
    Prev
    Next
    INDEX
    Explanations

    credit score

    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
    iday
    -0.09
    жд
    -0.09
    _ipc
    -0.09
    .Val
    -0.09
    SIM
    -0.09
     finals
    -0.09
     Rug
    -0.09
    èĤĵ
    -0.09
     Warm
    -0.09
    orgot
    -0.09
    POSITIVE LOGITS
     scores
    0.10
    åĪĨæķ°
    0.10
    æĪIJ绩
    0.10
     score
    0.09
    _scores
    0.09
    _score
    0.09
    绩
    0.09
    éĽĸ
    0.09
    opoulos
    0.08
    æĬĢæľ¯æ°´å¹³
    0.08
    Activations Density 0.031%

    No Known Activations