© 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. 55125
    Prev
    Next
    INDEX
    Explanations

    languages and origins

    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
     ins
    -0.09
    rut
    -0.09
    agon
    -0.08
     emb
    -0.08
     intens
    -0.07
    é¦Ĩ
    -0.07
    isos
    -0.07
     rew
    -0.07
    .Args
    -0.07
    åĪģ
    -0.07
    POSITIVE LOGITS
    ä¿Ĺ
    0.10
    大è§Ħ模
    0.09
    roe
    0.09
    à¸Ĩ
    0.09
    yro
    0.09
    à¹Ħà¸Ł
    0.08
    .ON
    0.08
     McGr
    0.08
    èĢģæŧ
    0.08
     Loch
    0.08
    Activations Density 0.064%

    No Known Activations