© 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. 12-TRANSCODER-HP
    7. 22399
    Prev
    Next
    INDEX
    Explanations

    customer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¯į
    -0.29
    Tech
    -0.28
    æĺ¼
    -0.27
    å·¥ç¨ĭå¸Ī
    -0.26
    TERN
    -0.25
    è©ŀ
    -0.25
    ington
    -0.24
     nights
    -0.24
    æ°ij
    -0.24
    AMPLE
    -0.24
    POSITIVE LOGITS
    ä¸Ģä¸ĭåŃIJ
    0.29
    ä¸Ģä¸ĭåŃIJå°±
    0.27
     addObject
    0.27
    evity
    0.26
    淹没
    0.26
    agara
    0.26
    ä¾
    0.26
     attached
    0.26
    æĢİä¹Īæł·
    0.26
    vation
    0.25
    Activations Density 0.005%

    No Known Activations