© 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. 63557
    Prev
    Next
    INDEX
    Explanations

    drug offenses and use

    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
    åħľ
    -0.10
    è®®
    -0.10
    vak
    -0.10
    soles
    -0.09
    DSL
    -0.09
    åĮłå¿ĥ
    -0.09
    æ±ľ
    -0.09
    _tra
    -0.09
    blocking
    -0.09
    razy
    -0.09
    POSITIVE LOGITS
    ERA
    0.09
     McCarthy
    0.08
    大声
    0.08
    era
    0.08
    éĩįéĩį
    0.08
    纪念
    0.08
    è¿ĻæĶ¯
    0.08
    dash
    0.08
    çĬĬ
    0.07
    声
    0.07
    Activations Density 0.021%

    No Known Activations