© 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. 19083
    Prev
    Next
    INDEX
    Explanations

    safe and safety

    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
    åijĨ
    -0.10
    åĩ¯
    -0.09
    æĪĸå¤ļ
    -0.09
    éĤ£å°±æĺ¯
    -0.09
    éĤ£éĩĮ
    -0.08
    èĹIJ
    -0.08
    åĩ±
    -0.08
    çĽIJ
    -0.08
    SPORT
    -0.08
    缴åĪ°
    -0.08
    POSITIVE LOGITS
    顾èĻij
    0.10
    è¿ĩåħ³
    0.09
    ä¸įçĶ¨æĭħå¿ĥ
    0.09
    subst
    0.09
     floor
    0.09
    æĥ³ä¸įåĪ°
    0.08
    æĶ¾å¿ĥ
    0.08
    æľīä»»ä½ķ
    0.08
    æ¶Īéĺ²å®īåħ¨
    0.08
    SAFE
    0.08
    Activations Density 0.029%

    No Known Activations