© 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. 49982
    Prev
    Next
    INDEX
    Explanations

    "it is" or "it was"

    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
    使åħ¶
    -0.11
    éĥ½å¾Ī
    -0.10
    ä¸įäºĨ
    -0.10
    SCO
    -0.10
    ðŁĶį
    -0.10
    æīĵæī®
    -0.10
    /Layout
    -0.09
    itos
    -0.09
    éĥ½éĿŀ常
    -0.09
    ç¢Į
    -0.09
    POSITIVE LOGITS
    rd
    0.10
    zelf
    0.10
     own
    0.09
    è¾ij
    0.09
    å°ĨåĨĽ
    0.08
    å®ıä¼Ł
    0.08
    l
    0.08
    注æĺİåĩºå¤Ħ
    0.08
    iable
    0.08
     невоз
    0.08
    Activations Density 0.029%

    No Known Activations