© 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. 3267
    Prev
    Next
    INDEX
    Explanations

    species names

    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
    è¿ħ
    -0.10
     Antar
    -0.10
     contracting
    -0.09
    oxid
    -0.09
    åĵ¡
    -0.08
    çĻ»åħ¥
    -0.08
    æĦīæĤ¦
    -0.08
    èĥĦ
    -0.08
    çĪµ
    -0.08
    éĶIJ
    -0.08
    POSITIVE LOGITS
    åıĹ害èĢħ
    0.09
    ä½ķå¿ħ
    0.09
    æ°ijå¿ĥ
    0.08
    Mine
    0.08
    eric
    0.08
    å®ľ
    0.08
    æ»ģ
    0.08
    dump
    0.08
    .mac
    0.08
     Amend
    0.08
    Activations Density 0.060%

    No Known Activations