© 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. 55069
    Prev
    Next
    INDEX
    Explanations

    scenery and terrain features

    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
    species
    -0.09
    æŁ½
    -0.09
    å®łçī©
    -0.09
    宫
    -0.09
    æĭ¢
    -0.09
    å§ĵ
    -0.09
    æķħ宫
    -0.09
    æµ·åºķ
    -0.08
    æĸ¹ä½į
    -0.08
    樽
    -0.08
    POSITIVE LOGITS
     landscapes
    0.14
    åľ°è²Į
    0.14
    é£İåħī
    0.14
    é£İæĻ¯
    0.14
     scenery
    0.14
     landscape
    0.13
    æĻ¯èī²
    0.13
    çĶ°åĽŃ
    0.13
    landscape
    0.12
    æĻ¯è§Ĥ
    0.12
    Activations Density 0.134%

    No Known Activations