© 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. 112705
    Prev
    Next
    INDEX
    Explanations

    sensory

    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
    istar
    -0.10
    âĺĨ
    -0.10
     Schwar
    -0.09
     extortion
    -0.09
     stump
    -0.09
     pars
    -0.09
     rem
    -0.09
    ück
    -0.08
     stellar
    -0.08
     вÑĭп
    -0.08
    POSITIVE LOGITS
     Sens
    0.21
     sensual
    0.19
     sens
    0.18
    SENS
    0.16
     sensory
    0.16
     sensing
    0.14
     sensible
    0.13
     Sensor
    0.12
     Sense
    0.12
     sensitivity
    0.12
    Activations Density 0.009%

    No Known Activations