© 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. 28053
    Prev
    Next
    INDEX
    Explanations

    cultural biases and assumptions

    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
    ssi
    -0.10
    æīĢæıIJä¾Ľ
    -0.10
    å¾Īæ¸ħæ¥ļ
    -0.09
    ç§ĺå¯Ĩ
    -0.09
    éĢĤ度
    -0.09
    ãĥĦ
    -0.09
     Secrets
    -0.09
     misunderstood
    -0.09
    çķľ
    -0.08
    è°Ĭ
    -0.08
    POSITIVE LOGITS
    è§Ĥ念
    0.14
     bias
    0.11
     biases
    0.11
    çĭŃ
    0.11
     assumptions
    0.10
    bias
    0.10
    çªģçł´
    0.10
    æĢĿç»´
    0.10
    çī¢åĽº
    0.10
    èĢģæŧ
    0.10
    Activations Density 0.076%

    No Known Activations