© 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. 51148
    Prev
    Next
    INDEX
    Explanations

    shaving units

    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
    usk
    -0.09
    åĪĨè£Ĥ
    -0.09
    amina
    -0.08
     pres
    -0.08
    OVER
    -0.08
    á»Ħ
    -0.08
    naire
    -0.08
    lobber
    -0.08
    å§ĭç»Īä¿ĿæĮģ
    -0.08
    ัว
    -0.08
    POSITIVE LOGITS
    åŃIJéĩĮ
    0.11
    èĦ¸
    0.11
    agar
    0.10
    æİīäºĨ
    0.10
    -faced
    0.09
    BOSE
    0.09
    æ³ł
    0.09
    inka
    0.09
    ળ
    0.09
    è¹Ń
    0.09
    Activations Density 0.004%

    No Known Activations