© 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. 88478
    Prev
    Next
    INDEX
    Explanations

    diverse news/current events

    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
    sla
    -0.30
    åĪ°è¿ĻéĩĮ
    -0.27
     Laure
    -0.27
     burg
    -0.26
    _beg
    -0.26
    LED
    -0.26
    æĺ¯ä¸įåı¯èĥ½
    -0.26
     thá»ı
    -0.25
     threatening
    -0.25
    yla
    -0.24
    POSITIVE LOGITS
    ç³Ĭæ¶Ĥ
    0.27
    workspace
    0.26
    repeat
    0.25
    override
    0.25
    	yield
    0.24
    æĽ´åĬł
    0.24
     Comparator
    0.23
    æķĻèģĮå·¥
    0.23
    å®ŀåľ¨
    0.23
    æĽ´
    0.23
    Activations Density 0.007%

    No Known Activations