© 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. 34377
    Prev
    Next
    INDEX
    Explanations

    warning signs

    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
    çķ¥
    -0.09
    çĦ°
    -0.09
    èĦŀ
    -0.09
    emax
    -0.09
    æħ
    -0.09
    Shield
    -0.09
    itionally
    -0.09
     skÅĤ
    -0.08
    åħ®
    -0.08
    гÑĢан
    -0.08
    POSITIVE LOGITS
    çīĮ
    0.17
    çīĮåŃIJ
    0.14
    æłĩè¯Ń
    0.14
    æĭĽçīĮ
    0.12
    åĮ¾
    0.11
     signs
    0.11
     sign
    0.10
    éĨĴ缮
    0.09
    æĮĤåľ¨
    0.09
    åĦĨ
    0.09
    Activations Density 0.051%

    No Known Activations