© 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. 35350
    Prev
    Next
    INDEX
    Explanations

    velocity and silkiness

    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
    sWith
    -0.11
    noon
    -0.10
    åijĹ
    -0.09
    ATIC
    -0.09
    ниÑĩ
    -0.09
    stract
    -0.08
    istory
    -0.08
    è°¢
    -0.08
    ä»¥äººä¸ºæľ¬
    -0.08
    yas
    -0.08
    POSITIVE LOGITS
    çªĸ
    0.09
    å°ı康社ä¼ļ
    0.09
    è¹Ī
    0.09
    ated
    0.08
    ----------------------------------------------------------------------------
    0.08
    触åıĬ
    0.08
    ×ķת
    0.08
    æ·±å¤Ħ
    0.08
    ç§ĥ
    0.08
    ocities
    0.08
    Activations Density 0.011%

    No Known Activations