© 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. 97803
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    otive
    -0.28
     revolving
    -0.25
    èĤ¡
    -0.24
    èĦī
    -0.24
    åĦ¿å¥³
    -0.24
    eria
    -0.24
    æĿľåħ°
    -0.24
    ãģĬãģĭãģĴ
    -0.23
    cerpt
    -0.23
    èĹ
    -0.23
    POSITIVE LOGITS
    obs
    0.27
    .Conn
    0.27
    nets
    0.25
     observation
    0.25
    ä¸įèĥ½åĨį
    0.25
    ä½łåĸľæ¬¢
    0.25
     obs
    0.25
    ä¸įåĨį
    0.24
    å°±çŁ¥éģĵ
    0.24
    éŃĶæ³ķå¸ĪåĴĮ
    0.24
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.