© 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. 33239
    Prev
    Next
    INDEX
    Explanations

    names ending in 'is' or 'os'

    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
    LEM
    -0.09
    è§Ĩ
    -0.08
    SPATH
    -0.08
    rod
    -0.08
    ãĤ·ãĥ³
    -0.08
    ç¾İéºĹ
    -0.08
     pard
    -0.07
     much
    -0.07
    FAQ
    -0.07
    åĭĴ
    -0.07
    POSITIVE LOGITS
    èĩ¾
    0.10
     dÃłng
    0.10
    请éĢīæĭ©
    0.10
    åĿıäºĭ
    0.10
    itud
    0.10
    èĵij
    0.10
    çĤ¸å¼¹
    0.09
    é¹ģ
    0.09
    椽
    0.09
    æ¸İ
    0.09
    Activations Density 0.006%

    No Known Activations