© 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. 98090
    Prev
    Next
    INDEX
    Explanations

    speaking, writing

    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
    ä¸įåĪ°
    -0.28
    ighted
    -0.26
    WAY
    -0.26
    ä¸ĢéŨ
    -0.26
    åĪ°äºĨ
    -0.26
    大éģĵ
    -0.26
    人å¿ĥ
    -0.26
    assador
    -0.25
    æ¯į
    -0.25
    åĮºåĨħ
    -0.24
    POSITIVE LOGITS
     distinguish
    0.25
     dem
    0.24
    rink
    0.23
    appName
    0.23
    uite
    0.23
    ala
    0.23
    obo
    0.23
    çļĦçIJĨ解
    0.23
     ND
    0.23
    åĿĩçĶ±
    0.23
    Activations Density 0.000%

    No Known Activations