© 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. 56917
    Prev
    Next
    INDEX
    Explanations

    running for office

    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
    ç¸
    -0.09
    翳
    -0.09
    çĥ«
    -0.09
     назад
    -0.08
    å®īéĿĻ
    -0.08
     concess
    -0.08
    ture
    -0.08
    å¤ļåªĴä½ĵ
    -0.08
    è§Ĥ
    -0.08
    _VEC
    -0.08
    POSITIVE LOGITS
    ç«ŀéĢī
    0.21
    åĢĻéĢī人
    0.19
    åĢĻéĢī
    0.16
    éĢī举
    0.16
     election
    0.15
     candidates
    0.14
     candidate
    0.14
     candidacy
    0.14
    æĶ¿åħļ
    0.14
    -election
    0.13
    Activations Density 0.261%

    No Known Activations