© 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. 6491
    Prev
    Next
    INDEX
    Explanations

    online

    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
    -être
    -0.10
    ively
    -0.10
    mate
    -0.10
    icit
    -0.10
    éķ¿è¿ľ
    -0.09
    ials
    -0.09
    ful
    -0.09
    ãģĻãģ§ãģ«
    -0.09
    finder
    -0.09
    åįĬå²Ľ
    -0.09
    POSITIVE LOGITS
    /off
    0.13
    ÑģÑĮ
    0.10
    WARDS
    0.10
    ein
    0.10
    ÑĢÑĥж
    0.10
    wers
    0.10
    yun
    0.09
    entifier
    0.09
    /out
    0.09
    ega
    0.09
    Activations Density 0.025%

    No Known Activations