© 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. 27151
    Prev
    Next
    INDEX
    Explanations

    financial consequences

    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
    å¦Ĥæŀľä¸į
    -0.10
    ERIC
    -0.10
    ardy
    -0.09
    èµ·æĿ¥
    -0.09
    ä¸įåĩºæĿ¥
    -0.09
    èµ·æĿ¥äºĨ
    -0.09
    ernet
    -0.09
    çĶ¬
    -0.09
    icens
    -0.09
    -rounded
    -0.09
    POSITIVE LOGITS
    æİī
    0.14
    åİŁåĽłæĺ¯
    0.12
    æİīäºĨ
    0.11
    åĩºå±Ģ
    0.10
    å¹²åĩĢ
    0.09
    åİŁåĽł
    0.09
    æŁ¥çľĭæĽ´å¤ļ
    0.09
    主è¦ģåİŁåĽł
    0.09
    bum
    0.09
    æī¿åıĹ
    0.09
    Activations Density 0.236%

    No Known Activations