© 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. 111657
    Prev
    Next
    INDEX
    Explanations

    random text snippets

    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
    æĬĬ她
    -0.28
     WHATSOEVER
    -0.27
    æĭ³å¤´
    -0.25
    amespace
    -0.24
     bindActionCreators
    -0.23
    ãĤĴè¦ĭãģĽ
    -0.23
     caul
    -0.23
     _:
    -0.23
    å§Ķå®£ä¼łéĥ¨
    -0.23
    phans
    -0.23
    POSITIVE LOGITS
    еÑĩ
    0.28
    ennes
    0.27
    éħ¶
    0.25
     ven
    0.24
    Lens
    0.24
    ven
    0.24
    é¹ĥ
    0.23
    -root
    0.23
    ë¥ľ
    0.23
    vere
    0.23
    Activations Density 0.017%

    No Known Activations