© 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. 54372
    Prev
    Next
    INDEX
    Explanations

    legal text, code, notice

    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
    ingly
    -0.13
    sWith
    -0.10
    çĦ¶æĺ¯
    -0.10
    /her
    -0.09
    reich
    -0.09
    lan
    -0.09
    agh
    -0.08
     kém
    -0.08
    æѤåĪ»
    -0.08
    lik
    -0.08
    POSITIVE LOGITS
    istic
    0.15
    -minded
    0.13
    itarian
    0.12
     minded
    0.11
    itas
    0.11
    istically
    0.11
    /legal
    0.11
    å·¥ä½ľèĢħ
    0.11
    endar
    0.10
    ities
    0.10
    Activations Density 0.021%

    No Known Activations