© 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. 14760
    Prev
    Next
    INDEX
    Explanations

    figure out why

    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
     Harr
    -0.08
     exposition
    -0.08
     prere
    -0.08
     uncomp
    -0.07
     inconvenient
    -0.07
    bak
    -0.07
    Rated
    -0.07
    Clar
    -0.07
    alf
    -0.07
     roughly
    -0.07
    POSITIVE LOGITS
     finger
    0.32
     Finger
    0.25
    finger
    0.22
     pinpoint
    0.18
     nail
    0.16
     fing
    0.16
     fingert
    0.15
     exact
    0.14
     fingers
    0.14
     why
    0.12
    Activations Density 0.010%

    No Known Activations