© 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. 4265
    Prev
    Next
    INDEX
    Explanations

    Ethnologue reports and species lists

    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
    äºĴ
    -0.09
    æķ¬
    -0.09
    çĶ¨é¤IJ
    -0.09
    REAK
    -0.09
    å¥
    -0.09
    åIJİå¤ĩ
    -0.08
    çµķ
    -0.08
     Macros
    -0.08
    çķĪ
    -0.08
     Ont
    -0.08
    POSITIVE LOGITS
    æªĢ
    0.10
    enco
    0.10
    ardon
    0.09
    åĪĽ
    0.09
    åĽŀéģ¿
    0.09
    goo
    0.09
     Carly
    0.08
    stellung
    0.08
    人å±ħ
    0.08
    æĢ¥
    0.08
    Activations Density 0.007%

    No Known Activations