© 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. 22825
    Prev
    Next
    INDEX
    Explanations

    cares and concern

    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
    åı¯èĥ½æĢ§
    -0.09
    åĨĹ
    -0.09
    доÑĢ
    -0.09
    æĪŁ
    -0.08
    axy
    -0.08
    etto
    -0.08
    ç¼ĺ
    -0.08
    ä¸įå¿ħ
    -0.08
    æĹłéľĢ
    -0.08
     IRS
    -0.08
    POSITIVE LOGITS
    åħ³å¿ĥ
    0.12
    Concern
    0.10
    åľ¨ä¹İ
    0.10
    羣çĪ±
    0.10
     Concern
    0.10
    åħ³åĪĩ
    0.10
    大åĪĩ
    0.10
     concern
    0.10
    åħ³æĢĢ
    0.09
    çļĦåħ³æ³¨
    0.09
    Activations Density 0.048%

    No Known Activations