© 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. 33401
    Prev
    Next
    INDEX
    Explanations

    admit that

    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
     trib
    -0.10
    ule
    -0.09
     Hok
    -0.09
    key
    -0.08
    tat
    -0.08
     formerly
    -0.08
    ahoo
    -0.08
    rend
    -0.08
    ende
    -0.08
     Rubber
    -0.08
    POSITIVE LOGITS
     inward
    0.12
     internally
    0.11
    lass
    0.11
     aloud
    0.10
     Beats
    0.10
    olley
    0.10
     saddle
    0.10
     Grat
    0.10
    	that
    0.10
    oui
    0.10
    Activations Density 0.003%

    No Known Activations