© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 27141
    Prev
    Next
    INDEX
    Explanations

    sensual suggestive or intimate descriptions

    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
     Fucked
    -0.13
     ejac
    -0.13
     dicks
    -0.13
     sperm
    -0.13
     shitty
    -0.12
     raping
    -0.12
     raped
    -0.12
     poop
    -0.12
     pee
    -0.12
     piss
    -0.11
    POSITIVE LOGITS
     sensual
    0.22
     sens
    0.21
     sed
    0.19
     langu
    0.18
     flirt
    0.18
     provocative
    0.18
     whisper
    0.17
     sul
    0.17
     tantal
    0.17
     suggestive
    0.17
    Activations Density 0.018%

    No Known Activations