© 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. 50724
    Prev
    Next
    INDEX
    Explanations

    Doctor followed by name or title

    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
    è¢ľ
    -0.10
    elin
    -0.09
     khỼp
    -0.09
    igham
    -0.08
    ØŃÙħ
    -0.08
    å§ĭ
    -0.08
    ëģĶ
    -0.08
    Court
    -0.08
    REF
    -0.08
     акÑĤÑĥ
    -0.08
    POSITIVE LOGITS
    stown
    0.10
    çĴľ
    0.09
    ibus
    0.09
    acle
    0.09
    sonian
    0.08
    åı¯æĥľ
    0.08
    èģĮåĬ¡
    0.08
    bate
    0.08
    æĢ»å±Ģ
    0.08
    ãģij
    0.08
    Activations Density 0.026%

    No Known Activations