© 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. 4131
    Prev
    Next
    INDEX
    Explanations

    whom

    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
    åħ¶å®ĥéĹ®é¢ĺ
    -0.08
    ais
    -0.08
    erts
    -0.08
    ily
    -0.08
    ä¸į失
    -0.07
    èĤī
    -0.07
     this
    -0.07
    er
    -0.07
     Carm
    -0.07
    tons
    -0.07
    POSITIVE LOGITS
    èłĸ
    0.10
    è·Łä»ĸ
    0.10
    ominated
    0.10
    SCII
    0.10
     Oval
    0.09
    çķİ
    0.09
    çħ§äº®
    0.09
    PACE
    0.09
    _PHP
    0.09
    adden
    0.09
    Activations Density 0.019%

    No Known Activations