© 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. 2082
    Prev
    Next
    INDEX
    Explanations

    home related words

    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
     Logical
    -0.26
    ACITY
    -0.25
    社ä¼ļåIJĦçķĮ
    -0.25
    baum
    -0.23
    å¾Ĺ天çĭ¬åİļ
    -0.23
    éĴµ
    -0.23
    logical
    -0.22
    Logical
    -0.21
     Reich
    -0.21
     logical
    -0.21
    POSITIVE LOGITS
    -oriented
    0.27
    -made
    0.26
     home
    0.26
    -friendly
    0.25
    -pl
    0.25
    å®īå±ħ
    0.25
    è£ħä¿®
    0.24
    åĨĻä½ľ
    0.24
    -level
    0.24
    家å±ħ
    0.24
    Activations Density 0.019%

    No Known Activations