© 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. 30291
    Prev
    Next
    INDEX
    Explanations

    worried aboutafraid tomake layouts

    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
     Wig
    -0.09
    Pont
    -0.08
    eki
    -0.08
     Harm
    -0.08
     amor
    -0.08
     casc
    -0.08
     thirst
    -0.08
    ONO
    -0.08
     Sem
    -0.08
     prec
    -0.08
    POSITIVE LOGITS
     Hass
    0.11
    loe
    0.11
    arl
    0.10
    olor
    0.10
    809
    0.10
     Tat
    0.10
     assembly
    0.10
    uster
    0.10
     Assembly
    0.09
     fallout
    0.09
    Activations Density 0.001%

    No Known Activations