© 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. 4270
    Prev
    Next
    INDEX
    Explanations

    left/right and remaining

    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
    awe
    -0.09
    ijke
    -0.08
    ocre
    -0.08
     saint
    -0.08
    onne
    -0.08
    ocs
    -0.08
    avan
    -0.08
    olf
    -0.08
    Ķ
    -0.08
    hit
    -0.07
    POSITIVE LOGITS
    /right
    0.23
    most
    0.23
    -handed
    0.21
    -hand
    0.21
    ward
    0.21
    overs
    0.20
    wards
    0.19
    -wing
    0.18
    arrow
    0.17
    enant
    0.17
    Activations Density 0.044%

    No Known Activations