© 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. 88487
    Prev
    Next
    INDEX
    Explanations

    Software and programming related

    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
    åį¯
    -0.25
     combination
    -0.24
     revolutionary
    -0.24
     society
    -0.24
    åľ¨éĤ£éĩĮ
    -0.24
    Aff
    -0.23
     democracy
    -0.23
    ista
    -0.23
    ç¼
    -0.23
     economy
    -0.23
    POSITIVE LOGITS
    linky
    0.27
    ações
    0.27
    è¯ī
    0.26
    çek
    0.26
    Ñģки
    0.26
    æĿ¡
    0.26
    ahren
    0.25
    coins
    0.25
    hcp
    0.25
    boo
    0.25
    Activations Density 0.003%

    No Known Activations