© 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. 15799
    Prev
    Next
    INDEX
    Explanations

    height and weight measurements

    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
     (--
    -0.12
     crud
    -0.12
    gom
    -0.12
    dsl
    -0.11
     literal
    -0.11
     physically
    -0.11
     anatom
    -0.11
     enlarg
    -0.11
    atis
    -0.11
    /address
    -0.11
    POSITIVE LOGITS
     compared
    0.09
     TBD
    0.09
     scr
    0.08
    ish
    0.08
     shorter
    0.08
    ÑıÑĤ
    0.08
     completion
    0.08
    lbs
    0.08
    chap
    0.08
    ,
    0.08
    Activations Density 0.004%

    No Known Activations