© 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. 2120
    Prev
    Next
    INDEX
    Explanations

    target and object locations

    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
     resid
    -0.25
    -editor
    -0.23
     explic
    -0.23
    oice
    -0.22
    dff
    -0.22
    holiday
    -0.21
     neighbour
    -0.21
     démarch
    -0.21
    ings
    -0.21
     definit
    -0.21
    POSITIVE LOGITS
    缮æłĩä»»åĬ¡
    0.39
    æĮijæĪĺ
    0.36
     targets
    0.35
    éĿ¶
    0.34
     target
    0.34
    targets
    0.33
     TARGET
    0.33
    缮æłĩ
    0.32
    /target
    0.32
    ä»»åĬ¡
    0.32
    Activations Density 0.072%

    No Known Activations