© 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. 23579
    Prev
    Next
    INDEX
    Explanations

    simply followed by description

    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
    Ñĥни
    -0.10
    çī¹æ®ĬæĥħåĨµ
    -0.10
     maybe
    -0.09
    eneral
    -0.09
    _HAL
    -0.09
    çĿ¦
    -0.09
    tet
    -0.09
    hire
    -0.08
    RITE
    -0.08
    ä»ħä¾Ľ
    -0.08
    POSITIVE LOGITS
     simply
    0.10
    åĩºè·¯
    0.10
     Simply
    0.09
    -minded
    0.09
    å°±æĺ¯åĽłä¸º
    0.09
    tha
    0.09
     Bever
    0.09
    pta
    0.08
    å±ij
    0.08
    è¶ĬæĿ¥
    0.08
    Activations Density 0.040%

    No Known Activations