© 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. 48239
    Prev
    Next
    INDEX
    Explanations

    consent, choice, willingly

    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
    貫
    -0.09
    è´¯
    -0.09
    BOR
    -0.09
    å¯Ħ
    -0.08
    çĥ©
    -0.08
    hop
    -0.08
    ÑģÑĤи
    -0.08
     Civ
    -0.08
    _SENS
    -0.08
     pret
    -0.07
    POSITIVE LOGITS
    èĩªæĦ¿
    0.31
    主åĬ¨
    0.24
    èĩªè§ī
    0.21
     voluntary
    0.20
     voluntarily
    0.20
    èĩªä¸»
    0.18
    主åĭķ
    0.18
    主åĬ¨æĢ§
    0.16
     willingly
    0.15
    èĩªåıij
    0.15
    Activations Density 0.195%

    No Known Activations