© 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. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 112519
    Prev
    Next
    INDEX
    Explanations

    conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å±ħçĦ¶
    -0.29
    redirect
    -0.28
    Compact
    -0.27
    ocket
    -0.27
     perhaps
    -0.26
    Disp
    -0.26
    绣çŃ¹æİ¨è¿Ľ
    -0.26
    è´¼
    -0.26
     realise
    -0.25
    åĩĨ
    -0.25
    POSITIVE LOGITS
    aģı
    0.28
    åĽ½åĨħå¸Ĥåľº
    0.27
    æ¯ıä¸Ģ次
    0.27
    åºľ
    0.26
     CAP
    0.25
    tor
    0.23
     teamwork
    0.23
    åѦåīį
    0.23
    ุ
    0.23
    ingly
    0.23
    Activations Density 0.080%

    No Known Activations