© 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. 2966
    Prev
    Next
    INDEX
    Explanations

    dimensional

    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
    xxxx
    -0.22
    pon
    -0.22
    Ps
    -0.22
    æ°Ł
    -0.21
     CENTER
    -0.21
    çįĴ
    -0.20
    .INTERNAL
    -0.20
     xxxx
    -0.20
     Buccane
    -0.20
    çĥĻ
    -0.20
    POSITIVE LOGITS
    ç®Ģ称
    0.42
    (IT
    0.31
    (IS
    0.30
    (IP
    0.29
    (I
    0.29
    (V
    0.26
    (R
    0.26
    (OS
    0.25
    (W
    0.25
    inition
    0.25
    Activations Density 2.118%

    No Known Activations