© 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. 39005
    Prev
    Next
    INDEX
    Explanations

    stand + preposition

    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
    æ²»
    -0.09
    丧失
    -0.09
    è¿ľç¦»
    -0.08
    elda
    -0.08
    lineno
    -0.08
    客æĪ·æıIJä¾Ľ
    -0.08
    shed
    -0.08
    认æ¸ħ
    -0.08
    åŁºåĩĨ
    -0.08
    çĶľ
    -0.08
    POSITIVE LOGITS
    -alone
    0.10
    è±ī
    0.09
     Ñģобой
    0.09
    æĦıæĢĿ
    0.09
    -ie
    0.09
    åĬŁ
    0.09
    åģķ
    0.09
    æĺ¯ä¸Ģ座
    0.09
    ä¸Ģç«Ļ
    0.09
    á»ĺ
    0.09
    Activations Density 0.020%

    No Known Activations