© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29762
    Prev
    Next
    INDEX
    Explanations

    between two places or people

    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
    imus
    -0.09
    atro
    -0.09
    åħ¸
    -0.09
     incumb
    -0.09
    vir
    -0.08
    Them
    -0.08
    ums
    -0.08
    åĴ¸
    -0.08
    å±Ģéĥ¨
    -0.08
    è¯İ
    -0.08
    POSITIVE LOGITS
    伺
    0.11
    è¾IJå°Ħ
    0.09
    èĺħ
    0.09
    è§ij
    0.08
    Åijs
    0.08
    ÑĨев
    0.08
    åħ¼é¡¾
    0.08
    ä¾¿å®ľ
    0.08
    æݧ
    0.08
    AAF
    0.08
    Activations Density 0.044%

    No Known Activations