© 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. 19981
    Prev
    Next
    INDEX
    Explanations

    slow performance or speed issue

    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
    å¢ħ
    -0.09
    åĪ©äºļ
    -0.09
    amen
    -0.09
    ÑģÑĤÑĥп
    -0.09
    acic
    -0.09
    ilio
    -0.08
    ialized
    -0.08
     halls
    -0.08
    latable
    -0.08
    éĶĻäºĨ
    -0.08
    POSITIVE LOGITS
     rãi
    0.11
    poke
    0.11
    est
    0.11
    ernet
    0.11
    idge
    0.10
    ingly
    0.10
    lining
    0.10
    ish
    0.10
    itzer
    0.10
    ishly
    0.09
    Activations Density 0.014%

    No Known Activations