© 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. 3928
    Prev
    Next
    INDEX
    Explanations

    story or song details

    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
     screenplay
    -0.12
    /script
    -0.11
     Estr
    -0.10
     script
    -0.10
     scripting
    -0.09
     Artists
    -0.09
    artists
    -0.09
     quoted
    -0.09
     relev
    -0.09
     Straw
    -0.09
    POSITIVE LOGITS
     longing
    0.17
     love
    0.14
     lament
    0.13
     praise
    0.13
     praises
    0.12
     ode
    0.12
     transient
    0.12
     lover
    0.12
     describing
    0.12
     metaphor
    0.12
    Activations Density 0.134%

    No Known Activations