© 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. 53235
    Prev
    Next
    INDEX
    Explanations

    NOT followed by a descriptor

    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
    æľ¬èº«å°±
    -0.09
    ings
    -0.09
    LLU
    -0.08
    ILD
    -0.08
    [email
    -0.08
    otre
    -0.08
    æģ«
    -0.08
    ocks
    -0.08
    otent
    -0.08
     Colomb
    -0.08
    POSITIVE LOGITS
    åĬŃ
    0.10
     NOT
    0.09
    NOT
    0.09
    éķĩæĶ¿åºľ
    0.09
    山寨
    0.08
    æĮīçħ§
    0.08
    éĢīè´Ń
    0.08
    大å¹ħ度
    0.08
     {}.
    0.08
    isser
    0.08
    Activations Density 0.032%

    No Known Activations