© 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. 88487
    Prev
    Next
    INDEX
    Explanations

    fear and terror

    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
     frustrations
    -0.13
     embarrass
    -0.12
     frustr
    -0.11
     frustrating
    -0.11
     frustrated
    -0.11
     Proud
    -0.11
     Weg
    -0.10
     disappoint
    -0.10
     frustration
    -0.10
     impatient
    -0.10
    POSITIVE LOGITS
     fear
    0.59
     terrified
    0.53
     Fear
    0.52
     frightened
    0.51
     scared
    0.51
     fearful
    0.50
    Fear
    0.47
     fearing
    0.42
     terror
    0.42
     fears
    0.41
    Activations Density 0.351%

    No Known Activations