© 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. 23261
    Prev
    Next
    INDEX
    Explanations

    Nicky/Nicki names

    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
    iska
    -0.09
     temper
    -0.08
     Household
    -0.08
    cult
    -0.08
    ning
    -0.08
    est
    -0.08
    ifer
    -0.07
    åĪ»èĭ¦
    -0.07
     comma
    -0.07
    _ticks
    -0.07
    POSITIVE LOGITS
    æī¶è´«å·¥ä½ľ
    0.10
    åĬ«
    0.10
    æ¸IJ
    0.10
    InitStruct
    0.09
    æļĿ
    0.09
    使åij½
    0.09
    çĻ»è®°
    0.09
     иÑģÑĤоÑĢии
    0.09
    prit
    0.09
     اÙĦÙħÙĩ
    0.09
    Activations Density 0.002%

    No Known Activations