© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90638
    Prev
    Next
    INDEX
    Explanations

    states of completion or closure

    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
     Bak
    -0.13
     зав
    -0.11
    Marks
    -0.11
    AbsolutePath
    -0.10
    Pane
    -0.10
     #:
    -0.10
     baik
    -0.10
     Cham
    -0.10
     Cros
    -0.10
     Ley
    -0.10
    POSITIVE LOGITS
     Cottage
    0.08
    oir
    0.08
     Gir
    0.08
     proverb
    0.08
     betray
    0.08
    ores
    0.08
    enes
    0.08
    ambi
    0.07
    hn
    0.07
    -l
    0.07
    Activations Density 0.186%

    No Known Activations