© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51844
    Prev
    Next
    INDEX
    Explanations

    imagination

    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
    uu
    -0.09
    ying
    -0.09
    ilm
    -0.09
    ÑıÑī
    -0.09
    ven
    -0.09
    ÙĤت
    -0.08
    ends
    -0.08
    age
    -0.08
    ols
    -0.08
    yo
    -0.08
    POSITIVE LOGITS
    istic
    0.13
    æ·±å¤Ħ
    0.10
    AndServe
    0.10
    ä¸įåĩºæĿ¥
    0.10
    agini
    0.09
    isco
    0.09
     Ñģебе
    0.09
    Ñħи
    0.09
    /Graphics
    0.09
    PURE
    0.09
    Activations Density 0.015%

    No Known Activations