© 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. 97487
    Prev
    Next
    INDEX
    Explanations

    creative hobbies

    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¸į平衡
    -0.28
    ics
    -0.27
     BJ
    -0.25
    bitrary
    -0.25
    bn
    -0.25
    Shield
    -0.24
    BJ
    -0.24
     паÑĢÑĤ
    -0.24
    balances
    -0.24
    Identifier
    -0.24
    POSITIVE LOGITS
     infinit
    0.31
     Abyss
    0.28
    åĮºåŁŁåĨħ
    0.28
     MyBase
    0.25
    é²ľæĺİ
    0.25
    ä¸Ģæĺ¯
    0.25
    .pred
    0.25
     Doll
    0.25
    infra
    0.25
    arking
    0.24
    Activations Density 0.005%

    No Known Activations