© 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. 2873
    Prev
    Next
    INDEX
    Explanations

    approval processes

    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
    ally
    -0.36
    ical
    -0.27
    ãģĹãģ¾ãģĨ
    -0.26
    ALLY
    -0.25
    curring
    -0.24
    IMUM
    -0.23
    ically
    -0.23
    çļĦè¯Ŀé¢ĺ
    -0.23
    atically
    -0.22
    ed
    -0.21
    POSITIVE LOGITS
    ities
    0.30
    utions
    0.26
    istic
    0.24
    ties
    0.24
    ty
    0.24
    iesen
    0.24
    ites
    0.23
    ship
    0.23
    ution
    0.22
    çĪ±å¥½
    0.21
    Activations Density 0.009%

    No Known Activations