© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20008
    Prev
    Next
    INDEX
    Explanations

    think that

    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
    antal
    -0.09
    اجر
    -0.08
    AINS
    -0.08
    è¶ĬæĿ¥è¶Ĭå°ij
    -0.08
    Trap
    -0.07
    é¡»
    -0.07
     monstr
    -0.07
    flen
    -0.07
    hal
    -0.07
    åijĨ
    -0.07
    POSITIVE LOGITS
    æķ´é½IJ
    0.11
     Ðļи
    0.10
     thân
    0.09
    森æŀĹåħ¬åĽŃ
    0.09
    èĩªæķij
    0.09
    海峡
    0.09
    çķĻç»Ļ
    0.09
    说æĪij
    0.09
    çĪ±ç¾İ
    0.09
    ipl
    0.09
    Activations Density 0.036%

    No Known Activations