© 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. 6548
    Prev
    Next
    INDEX
    Explanations

    challenging traditional ideas

    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
    ifr
    -0.10
    rap
    -0.10
     invol
    -0.10
     outf
    -0.10
     иÑģп
    -0.09
     Ebony
    -0.09
     entr
    -0.09
     olive
    -0.09
    Abort
    -0.09
    hands
    -0.09
    POSITIVE LOGITS
     conventional
    0.38
     conventions
    0.34
     boundaries
    0.34
     traditional
    0.33
     barriers
    0.30
     convention
    0.29
     norms
    0.29
     assumptions
    0.27
    traditional
    0.25
     Traditional
    0.25
    Activations Density 0.184%

    No Known Activations