© 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. 23124
    Prev
    Next
    INDEX
    Explanations

    Demonstrate/indicate/show

    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
    ä¹ı
    -0.27
    åĵī
    -0.26
    延误
    -0.26
    è¾±
    -0.25
    ä¸ªå·¥ä½ľ
    -0.24
    erral
    -0.24
    沩
    -0.24
     currencies
    -0.23
    åĮºç®¡å§Ķä¼ļ
    -0.23
    oeff
    -0.23
    POSITIVE LOGITS
    临æŶ
    0.30
    容
    0.28
    _sock
    0.27
    .rstrip
    0.27
     absolute
    0.26
    tees
    0.26
    лÑĥÑĪ
    0.26
    Plain
    0.25
    uous
    0.25
    rics
    0.25
    Activations Density 0.002%

    No Known Activations