© 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. 97509
    Prev
    Next
    INDEX
    Explanations

    mission

    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
    izontal
    -0.29
    _mt
    -0.26
     MongoClient
    -0.26
    )._
    -0.25
    abis
    -0.25
    istributor
    -0.24
    propri
    -0.24
    æIJĶ
    -0.24
     specials
    -0.24
    autoload
    -0.24
    POSITIVE LOGITS
    rone
    0.28
    ieme
    0.27
    gil
    0.27
     accomplished
    0.27
    i
    0.27
    ra
    0.26
    ié
    0.26
     Young
    0.26
    ici
    0.25
    enda
    0.25
    Activations Density 0.174%

    No Known Activations