© 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. 4722
    Prev
    Next
    INDEX
    Explanations

    it

    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
     spontaneously
    -0.12
     spontaneous
    -0.11
     unofficial
    -0.11
     unpopular
    -0.11
    Dire
    -0.10
    )(*
    -0.10
     furthermore
    -0.10
     Dire
    -0.10
    arks
    -0.10
    DVD
    -0.10
    POSITIVE LOGITS
     unclear
    0.25
     ambiguous
    0.24
     difficult
    0.22
     obscured
    0.21
     ambiguity
    0.21
     ind
    0.20
     discern
    0.19
     uncertain
    0.19
     impossible
    0.18
     hard
    0.18
    Activations Density 0.111%

    No Known Activations