© 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. 29875
    Prev
    Next
    INDEX
    Explanations

    financial + responsibility, security, advisors, statement, product, performance, basis, wellbeing

    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
    ../../../
    -0.14
    ../../../../
    -0.10
    åŃIJéĩĮ
    -0.10
    icit
    -0.10
    ading
    -0.09
    ftime
    -0.09
    ../../
    -0.09
    èĪĴå¿ĥ
    -0.09
    èĬ±çĶŁ
    -0.09
    æŁ°
    -0.08
    POSITIVE LOGITS
    çĬ¶åĨµ
    0.12
    mente
    0.10
    s
    0.09
    ÙĬÙĪ
    0.09
    约æĿŁ
    0.08
    sun
    0.08
    ponsible
    0.08
     Luca
    0.08
    PropertyName
    0.08
    åŃ¦å®¶
    0.08
    Activations Density 0.014%

    No Known Activations