© 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. 4128
    Prev
    Next
    INDEX
    Explanations

    anonymous sexual dating

    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
    &eacute
    -0.11
    Ãĥ
    -0.11
     mädchen
    -0.10
    imu
    -0.10
    &apos
    -0.10
    &quot
    -0.10
    Â
    -0.10
    vae
    -0.10
    (http
    -0.10
     Thumb
    -0.10
    POSITIVE LOGITS
     âĦĸ
    0.12
     С
    0.09
     vice
    0.08
    Ñģ
    0.08
     âĨ
    0.08
     meiner
    0.08
     Gos
    0.08
    exemple
    0.08
     fore
    0.07
    wort
    0.07
    Activations Density 0.165%

    No Known Activations