© 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. 63070
    Prev
    Next
    INDEX
    Explanations

    interview

    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
    åıijå¸ĥåħ¬åijĬ
    -0.09
    udad
    -0.09
    éĢļæĬ¥
    -0.09
    åĽ¢ä¼Ļ
    -0.08
     ec
    -0.08
    ettel
    -0.08
    代åĬŀ
    -0.08
    дол
    -0.08
    trak
    -0.08
    å¤ĸåľ°
    -0.08
    POSITIVE LOGITS
    访è°Ī
    0.25
    éĩĩ访
    0.25
    ä¸ĵ访
    0.23
     interview
    0.21
    éĩĩ访æŶ
    0.21
     interviews
    0.21
    Interview
    0.20
     Interview
    0.19
    åıĹ访èĢħ
    0.18
     interviewed
    0.17
    Activations Density 0.081%

    No Known Activations