© 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. 49863
    Prev
    Next
    INDEX
    Explanations

    No Nut

    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
    çĺ¸
    -0.08
    รว
    -0.08
    顺çķħ
    -0.08
    _ROUT
    -0.08
    æ»Ķ
    -0.08
    ohn
    -0.08
    主è¦ģåĮħæĭ¬
    -0.08
    arty
    -0.08
    rees
    -0.07
    arte
    -0.07
    POSITIVE LOGITS
     Townsend
    0.09
    åĩºå¤Ħ
    0.08
    Ìģ
    0.08
    辦æ³ķ
    0.08
    æijĨ
    0.08
    ifix
    0.08
    -chan
    0.08
     безопаÑģноÑģÑĤи
    0.07
    人æ°ijç½ij
    0.07
    åİĭ缩
    0.07
    Activations Density 0.220%

    No Known Activations