© 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. 63112
    Prev
    Next
    INDEX
    Explanations

    neutrality and impartiality

    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
    ä¸įåłª
    -0.08
    è·µ
    -0.08
    imar
    -0.08
    å¹ħ
    -0.08
    RITE
    -0.08
     definitely
    -0.08
    æĺ¯æľī
    -0.07
    Destroy
    -0.07
    å½ĵåį³
    -0.07
    ASP
    -0.07
    POSITIVE LOGITS
    客è§Ĥ
    0.19
     neutrality
    0.17
    Neutral
    0.15
    neutral
    0.15
     neutral
    0.15
     Neutral
    0.15
    åħ¬æŃ£
    0.14
     impartial
    0.13
     unbiased
    0.13
    -neutral
    0.13
    Activations Density 0.051%

    No Known Activations