© 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. 28623
    Prev
    Next
    INDEX
    Explanations

    cookies, consent, registration

    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
     Griffin
    -0.08
     Trem
    -0.08
    ATTER
    -0.07
     verification
    -0.07
     Apr
    -0.07
    apos
    -0.07
     Buenos
    -0.07
    gon
    -0.07
    _cred
    -0.07
    iale
    -0.07
    POSITIVE LOGITS
    eger
    0.11
     consent
    0.11
    hir
    0.11
    IPP
    0.10
     pseud
    0.10
     exempt
    0.10
    ict
    0.10
     Rat
    0.10
    -desc
    0.10
    /control
    0.09
    Activations Density 0.330%

    No Known Activations