© 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. 23212
    Prev
    Next
    INDEX
    Explanations

    consecutive back-to-back

    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
    åħ¨åªĴä½ĵ
    -0.09
    UMB
    -0.09
     бÑİ
    -0.08
    plist
    -0.08
    å¤įå·¥
    -0.08
    åĵ¡
    -0.08
     Extras
    -0.08
    uide
    -0.08
    Plane
    -0.08
    oren
    -0.08
    POSITIVE LOGITS
    ä¿©
    0.09
    è·Łå¥¹
    0.09
    brero
    0.09
    å¸Ń
    0.09
    Gab
    0.09
    çĿ¦
    0.08
    å§Ĭ妹
    0.08
    athon
    0.08
    åĪĽä¸ĭ
    0.08
    ester
    0.08
    Activations Density 0.005%

    No Known Activations