© 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. 2600
    Prev
    Next
    INDEX
    Explanations

    cover song

    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
     authority
    -0.23
    修饰
    -0.23
     governing
    -0.22
     pit
    -0.22
     oracle
    -0.22
    eld
    -0.22
     authentic
    -0.21
     заÑĢегиÑģÑĤ
    -0.21
     disciplined
    -0.20
     unravel
    -0.20
    POSITIVE LOGITS
     fuels
    0.27
     theirs
    0.24
    ishly
    0.23
    songs
    0.23
    çĩĥæ²¹
    0.23
    auce
    0.23
     decks
    0.23
    è¶ħè¿ĩ
    0.23
    tain
    0.23
    /social
    0.23
    Activations Density 0.007%

    No Known Activations