© 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. 112290
    Prev
    Next
    INDEX
    Explanations

    rim

    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
    æĬ¥å¤į
    -0.26
    ebin
    -0.24
    ноÑģÑĤей
    -0.23
    å®
    -0.23
     covariance
    -0.23
    ì¡°
    -0.23
    logan
    -0.23
    	Int
    -0.22
    lessly
    -0.22
     signage
    -0.22
    POSITIVE LOGITS
    æĸ¹å¼ıè¿Ľè¡Į
    0.27
    Ѳ
    0.26
     cul
    0.24
    ÑIJ
    0.24
    lew
    0.23
    丫
    0.23
     refin
    0.23
    æĻ¶ä½ĵ
    0.23
    ÈĻi
    0.23
     оÑĤд
    0.23
    Activations Density 0.012%

    No Known Activations