© 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. 3372
    Prev
    Next
    INDEX
    Explanations

    relative clauses starting with who

    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
    å¼ķæĿ¥
    -0.10
    çŨ
    -0.10
    åħ¬çĽĬæĢ§
    -0.10
    æķ£åıij
    -0.09
    _elt
    -0.09
     Mash
    -0.09
    åıijåĩº
    -0.09
    æĭİ
    -0.09
    æĬ½åĩº
    -0.08
    室åĨħ
    -0.08
    POSITIVE LOGITS
    亲身
    0.18
    åıĤä¸İ
    0.17
    ç»ıåİĨè¿ĩ
    0.15
    åıĤä¸İèĢħ
    0.14
    è§ģè¯ģ
    0.13
    åıĥèĪĩ
    0.13
    åıĤä¸İåĪ°
    0.13
    亲èĩª
    0.12
    åıĤåĬł
    0.12
    äº²çľ¼
    0.12
    Activations Density 0.136%

    No Known Activations