© 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. 29794
    Prev
    Next
    INDEX
    Explanations

    slanted angles inclined tilted degrees

    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
     Lester
    -0.08
     Fowler
    -0.08
    Dou
    -0.08
     Curl
    -0.08
    uta
    -0.08
     Igor
    -0.08
     curl
    -0.08
     Whale
    -0.07
    perf
    -0.07
     filmy
    -0.07
    POSITIVE LOGITS
     downwards
    0.15
     toward
    0.14
     upward
    0.14
    forward
    0.14
     downward
    0.14
     towards
    0.13
     upwards
    0.13
     Towards
    0.13
     backwards
    0.13
     asympt
    0.13
    Activations Density 0.052%

    No Known Activations