© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8041
    Prev
    Next
    INDEX
    Explanations

    even numbers or positions

    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
    å§ĭç»Īä¿ĿæĮģ
    -0.09
    çĸ¾çĹħçļĦ
    -0.09
    isl
    -0.09
    orne
    -0.09
    ç¼Ļ
    -0.08
    åij¨åĽ´çļĦ
    -0.08
    quia
    -0.08
    åĽĽå¤Ħ
    -0.08
    aps
    -0.08
    DOWN
    -0.08
    POSITIVE LOGITS
    ness
    0.14
    -handed
    0.11
     parity
    0.10
    aled
    0.10
    NESS
    0.09
    ities
    0.09
    _odd
    0.09
    dbh
    0.08
    bum
    0.08
    arella
    0.08
    Activations Density 0.033%

    No Known Activations