© 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. 61706
    Prev
    Next
    INDEX
    Explanations

    forest and its surroundings

    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
    jective
    -0.10
    åĽŀäºĭ
    -0.09
    ãģ¹ãģį
    -0.09
    inding
    -0.09
    itt
    -0.09
    çķĽ
    -0.09
    ä¹ıåĬĽ
    -0.09
    ç¬ijèĦ¸
    -0.09
    ç½ij讯
    -0.09
    åħ¶æīĢ
    -0.09
    POSITIVE LOGITS
    æªİ
    0.11
    vÃŃ
    0.10
    wide
    0.10
    eners
    0.10
    alling
    0.09
    æĪij羣çļĦ
    0.09
    æ·±å¤Ħ
    0.09
    ening
    0.09
    виÑĤ
    0.09
    eson
    0.09
    Activations Density 0.022%

    No Known Activations