© 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. 22843
    Prev
    Next
    INDEX
    Explanations

    costs and consequences

    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
    Parents
    -0.10
     Parents
    -0.10
    èŀį为ä¸Ģä½ĵ
    -0.10
    èĸ¤
    -0.09
    èĥŀ
    -0.09
    è¿ĩåī©
    -0.08
    rame
    -0.08
    éĺIJ
    -0.08
    çķ
    -0.08
     wol
    -0.08
    POSITIVE LOGITS
    代价
    0.17
     toll
    0.14
    åIJİæŀľ
    0.11
    çīºçī²
    0.11
    æĪIJæľ¬
    0.10
     Toll
    0.10
     cost
    0.10
     consequences
    0.09
    çģµéŃĤ
    0.09
     consequence
    0.09
    Activations Density 0.077%

    No Known Activations