© 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. 114822
    Prev
    Next
    INDEX
    Explanations

    recording audio or video content

    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
     cameras
    -0.07
     Cameras
    -0.07
     Photographer
    -0.07
     photographers
    -0.06
     photo
    -0.06
     CAMERA
    -0.06
     photographer
    -0.06
    ilm
    -0.06
    ipa
    -0.06
     photography
    -0.06
    POSITIVE LOGITS
     performances
    0.14
    иÑĤелÑĮ
    0.13
     conversations
    0.12
     gameplay
    0.12
     Gameplay
    0.12
    icl
    0.12
    arte
    0.12
    VD
    0.12
     HWND
    0.12
    Dlg
    0.12
    Activations Density 0.025%

    No Known Activations