© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10328
    Prev
    Next
    INDEX
    Explanations

    inspecting and checking equipment

    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
    _CONNECTED
    -0.09
    åĸľæĤ¦
    -0.09
     Ralph
    -0.09
    è¦ģä¹Ī
    -0.08
    LAB
    -0.08
     Dig
    -0.08
    æ³¥
    -0.08
    /nav
    -0.08
    çĶľç¾İ
    -0.08
    acho
    -0.08
    POSITIVE LOGITS
    æ£ĢæŁ¥
    0.17
    æĺ¯åIJ¦æľī
    0.16
    æª¢æŁ¥
    0.14
     inspect
    0.14
    å·¡æŁ¥
    0.13
     inspection
    0.12
    æľī没æľī
    0.12
    Inspect
    0.12
    æŁ¥çľĭ
    0.11
    æŁ¥éªĮ
    0.11
    Activations Density 0.075%

    No Known Activations