© 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. 63279
    Prev
    Next
    INDEX
    Explanations

    yet [descriptor]

    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
     ÑĥÑģпеÑħ
    -0.09
    èĻ½çĦ¶
    -0.08
    åĢĴæĺ¯
    -0.08
    人ãĤĤ
    -0.08
     rear
    -0.08
    èĢĮåİ»
    -0.07
    ipient
    -0.07
    VER
    -0.07
    æŧ
    -0.07
    åŁºè°ĥ
    -0.07
    POSITIVE LOGITS
    ä¸į失
    0.12
    erno
    0.10
    åĩıåħį
    0.09
    usher
    0.09
    æīĭä¸Ĭ
    0.09
    ìĭľìĬ¤
    0.09
     obsÅĤ
    0.09
    åıĪèĥ½
    0.09
    ynos
    0.09
    ä¸Ĭå¹´
    0.09
    Activations Density 0.008%

    No Known Activations