© 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. 1694
    Prev
    Next
    INDEX
    Explanations

    encourage

    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¦ģæ±Ĥ
    -0.09
    agara
    -0.09
    ient
    -0.09
    æĸ°çīĪ
    -0.09
    ÑĢажа
    -0.08
    åħµåĬĽ
    -0.08
    geb
    -0.08
    led
    -0.08
     Regards
    -0.08
    aint
    -0.08
    POSITIVE LOGITS
    çĶ¨æĪ·æıIJä¾Ľ
    0.12
     ÑģамоÑģÑĤоÑı
    0.10
    大家åĪĨ享
    0.10
    èī¯æĢ§
    0.10
    /prom
    0.10
    éĵ¤
    0.09
    çļĦå°±æĺ¯
    0.09
    ç»Ĥ
    0.09
    ardin
    0.09
    åĭĻ
    0.09
    Activations Density 0.010%

    No Known Activations