© 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. 31907
    Prev
    Next
    INDEX
    Explanations

    renewal, replacement, regeneration, renovation

    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
    çĭĦ
    -0.11
    eria
    -0.10
    磫
    -0.10
    çľģéĴ±
    -0.09
    ouser
    -0.09
    èľ©
    -0.09
    å¯Ħ
    -0.09
    éŨçªĹ
    -0.09
    éģį
    -0.09
    ContentAlignment
    -0.09
    POSITIVE LOGITS
     replen
    0.17
    è¡¥åħħ
    0.15
    æĽ¿æį¢
    0.14
     replacements
    0.13
     replacement
    0.13
     replacing
    0.12
    æºIJæºIJä¸įæĸŃ
    0.12
    æºIJæºIJ
    0.12
     cycle
    0.12
     replace
    0.12
    Activations Density 0.142%

    No Known Activations