© 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. 130519
    Prev
    Next
    INDEX
    Explanations

    :

    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
    åıĸæ¶Ī
    -0.26
    Daily
    -0.25
    _scal
    -0.25
    俱
    -0.25
    itchen
    -0.25
    .workspace
    -0.24
    æ¯ıæĹ¥
    -0.24
     nearest
    -0.24
     Scal
    -0.24
    è½½
    -0.24
    POSITIVE LOGITS
    ide
    0.27
    ä¸Ģ份
    0.27
    ä¸ĭåİ»
    0.27
    oten
    0.26
    assi
    0.26
     pry
    0.25
    æŃ£æĺ¯
    0.25
    Dragging
    0.25
    ope
    0.25
    ruc
    0.24
    Activations Density 0.004%

    No Known Activations