© 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. 92123
    Prev
    Next
    INDEX
    Explanations

    vague guessing or hope

    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
     legitimate
    -0.10
     straightforward
    -0.10
     purposely
    -0.10
    lan
    -0.10
     Amp
    -0.10
     expressly
    -0.09
     avenues
    -0.09
     deliberately
    -0.09
    vect
    -0.09
     legitimately
    -0.09
    POSITIVE LOGITS
     vaguely
    0.28
     hoping
    0.25
     vague
    0.25
     guessing
    0.23
     arbitrarily
    0.22
     hope
    0.22
     guesses
    0.21
     randomly
    0.21
     guess
    0.21
     guessed
    0.20
    Activations Density 0.357%

    No Known Activations