© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115033
    Prev
    Next
    INDEX
    Explanations

    anime and manga

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
     fuck
    -0.11
     Fuck
    -0.11
     cocks
    -0.11
     fucks
    -0.11
     Cav
    -0.10
    Primitive
    -0.10
     Pivot
    -0.10
     shit
    -0.10
     Apt
    -0.10
    å·ŀ
    -0.10
    POSITIVE LOGITS
     Gundam
    0.27
     manga
    0.26
     anime
    0.24
    Anime
    0.23
     Anime
    0.22
     Sakura
    0.22
     Naruto
    0.21
    -sama
    0.20
     Kyoto
    0.20
    anime
    0.19
    Activations Density 0.216%

    No Known Activations