© 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. 57560
    Prev
    Next
    INDEX
    Explanations

    fight or against

    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
    è·ĥ
    -0.11
    çīĴ
    -0.10
    _COMMIT
    -0.09
    è²Ĥ
    -0.08
    äº¤æĽ¿
    -0.08
     Werk
    -0.08
    urance
    -0.08
    å¦ĥ
    -0.08
    éĢŁ
    -0.08
    amer
    -0.08
    POSITIVE LOGITS
    å¾Ĺä½ı
    0.09
    ForResult
    0.09
    insky
    0.09
    åĩĨå¤ĩ好
    0.09
     against
    0.09
    iner
    0.09
    çĪµå£«
    0.09
     back
    0.09
     PROVIDED
    0.09
    没å¿ħè¦ģ
    0.09
    Activations Density 0.022%

    No Known Activations