© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3104
    Prev
    Next
    INDEX
    Explanations

    words related to evolution

    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
    èģĶè°Ĭ
    -0.10
    ness
    -0.10
    åıijå±ķéĺ¶æ®µ
    -0.10
    ä¹Ķ丹
    -0.09
    ugg
    -0.09
    ocr
    -0.09
    çĩĶ
    -0.09
    棣
    -0.09
    å¢ī
    -0.08
    奴
    -0.08
    POSITIVE LOGITS
    arily
    0.13
    éĿ¢åīį
    0.10
    ALLY
    0.09
    -themed
    0.09
    ions
    0.09
    ically
    0.08
    Cro
    0.08
    /or
    0.08
    -inspired
    0.08
    enthal
    0.08
    Activations Density 0.022%

    No Known Activations