© 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. 20239
    Prev
    Next
    INDEX
    Explanations

    inheritance and legacy

    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
    èĩĨ
    -0.10
    å«©
    -0.09
     rough
    -0.09
    æ³Ľ
    -0.09
    æ³®
    -0.09
    æľªæĽ¾
    -0.09
    沿çĿĢ
    -0.09
     HOLDER
    -0.08
    rack
    -0.08
    åħĥæŦ
    -0.08
    POSITIVE LOGITS
     legacy
    0.21
     Legacy
    0.18
    éģĹ产
    0.17
    legacy
    0.17
    _legacy
    0.17
    Legacy
    0.16
    éģĹçķĻ
    0.15
    çķĻç»Ļ
    0.14
     inheritance
    0.12
    ä¸Ģå¥Ĺ
    0.11
    Activations Density 0.030%

    No Known Activations