© 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. 34110
    Prev
    Next
    INDEX
    Explanations

    pulp and paper production

    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
     Charg
    -0.09
    charg
    -0.09
     Attached
    -0.08
    PW
    -0.08
    DEFINE
    -0.08
    票
    -0.07
     bergen
    -0.07
    roof
    -0.07
     charg
    -0.07
     Punch
    -0.07
    POSITIVE LOGITS
    éĢłçº¸
    0.19
    纸
    0.13
     бÑĥм
    0.11
    纤维
    0.11
     pulp
    0.10
    Spread
    0.10
    ç´Ļ
    0.10
     Spread
    0.10
    åĩłå¼ł
    0.10
    ç¬ĭ
    0.10
    Activations Density 0.133%

    No Known Activations