© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1794
    Prev
    Next
    INDEX
    Explanations

    grant or granted permission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    -0.22
    ä»Ĺ
    -0.19
    çĹĩçĬ¶
    -0.19
    guards
    -0.19
    habit
    -0.19
    plies
    -0.19
    ffset
    -0.18
    çĹĩ
    -0.18
     predetermined
    -0.17
    curity
    -0.17
    POSITIVE LOGITS
    edly
    0.30
    ably
    0.23
    manship
    0.22
    chester
    0.21
    itud
    0.21
    isseur
    0.20
    ship
    0.20
    itude
    0.20
    !--
    0.20
    tee
    0.19
    Activations Density 0.015%

    No Known Activations