© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 7440
    Prev
    Next
    INDEX
    Explanations

    sweetheart, honey, your

    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
     dude
    -0.15
     Dude
    -0.14
     fucked
    -0.13
     dudes
    -0.12
     Fucked
    -0.11
     axiom
    -0.11
     pissed
    -0.11
     sir
    -0.11
    ymes
    -0.11
     newbie
    -0.11
    POSITIVE LOGITS
     honey
    0.13
     Honey
    0.12
     your
    0.10
     sweetheart
    0.09
     Your
    0.09
    rais
    0.09
     quil
    0.09
    struments
    0.08
    enton
    0.08
     Sevilla
    0.08
    Activations Density 0.070%

    No Known Activations