© 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. 62097
    Prev
    Next
    INDEX
    Explanations

    names beginning with av or sa

    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
    hausen
    -0.10
    åł¡
    -0.09
    æĢ¥äºİ
    -0.09
    orn
    -0.08
    otor
    -0.08
    èŁĨ
    -0.08
    å¢ĥ
    -0.08
     extr
    -0.08
     flop
    -0.08
    atrix
    -0.08
    POSITIVE LOGITS
    anni
    0.09
    æī¿
    0.09
    妫
    0.08
    cÃŃ
    0.08
    è´³
    0.08
    æ¶ij
    0.08
    rxjs
    0.08
    olley
    0.08
    íĸ¥
    0.08
     goggles
    0.08
    Activations Density 0.104%

    No Known Activations