© 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. 3013
    Prev
    Next
    INDEX
    Explanations

    disambiguation / .h / base

    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
    _SUITE
    -0.23
    çķ´
    -0.22
    stk
    -0.22
    izador
    -0.22
    айн
    -0.21
    ä¸ĸ纪
    -0.21
    izacion
    -0.20
    ä¸Ģ身
    -0.20
    house
    -0.20
    åħįéĻ¤
    -0.20
    POSITIVE LOGITS
    /msg
    0.26
    éģij
    0.23
    çłĶ究çĶŁ
    0.23
    åħĥç´ł
    0.22
    robe
    0.22
     Hashtable
    0.22
    ç¢
    0.21
     discourse
    0.21
    uÅŁ
    0.21
    numeric
    0.21
    Activations Density 0.004%

    No Known Activations