© 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. 30683
    Prev
    Next
    INDEX
    Explanations

    fish for harvesting

    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
     пеÑĢевод
    -0.10
    éĨª
    -0.10
    åĿIJçĿĢ
    -0.10
    å®ł
    -0.10
    çģ¯çģ«
    -0.09
    éĹ·
    -0.09
    (sd
    -0.09
     евÑĢ
    -0.09
    è´µ
    -0.09
    忽
    -0.09
    POSITIVE LOGITS
    éĩĩéĽĨ
    0.14
    éĩĩæijĺ
    0.12
    æĶ¶èİ·
    0.12
    éĩİ
    0.11
    æįķ
    0.11
    çĭ©
    0.11
    éĩĩ
    0.10
    åĽĽå¤Ħ
    0.10
    èįī
    0.10
    éĩİçĶŁ
    0.09
    Activations Density 0.060%

    No Known Activations