© 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. 117013
    Prev
    Next
    INDEX
    Explanations

    flashback memories visions

    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
    /material
    -0.10
     intellectually
    -0.09
    CCI
    -0.08
    eld
    -0.08
     Caj
    -0.08
     Moff
    -0.08
     bef
    -0.08
    IGO
    -0.08
     trusts
    -0.08
     sigh
    -0.08
    POSITIVE LOGITS
     visions
    0.40
     images
    0.34
     flashback
    0.34
     flashes
    0.33
     flash
    0.32
     vision
    0.31
     Images
    0.28
     envision
    0.27
    -flash
    0.26
    visions
    0.26
    Activations Density 0.055%

    No Known Activations