© 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. 23315
    Prev
    Next
    INDEX
    Explanations

    early life and career stages

    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
    æľīä¿¡å¿ĥ
    -0.10
    æ´µ
    -0.09
    åĪĨå¸ĥåľ¨
    -0.09
    æĢĿ
    -0.08
    æĸ°åĬ¨èĥ½
    -0.08
    æĺ¯éĿŀ
    -0.08
    éĺķ
    -0.08
    oul
    -0.08
    çĻ«çĹ«çĹħ
    -0.08
    æľīåħ´è¶£
    -0.08
    POSITIVE LOGITS
    -stage
    0.13
     stages
    0.12
    æĹ©æľŁ
    0.12
    enda
    0.11
    æĻļæľŁ
    0.11
     early
    0.11
    stage
    0.11
     late
    0.10
    early
    0.10
    éĺ¶æ®µ
    0.10
    Activations Density 0.061%

    No Known Activations