© 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. 98850
    Prev
    Next
    INDEX
    Explanations

    germany

    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
    i
    -0.33
    er
    -0.32
    ter
    -0.29
    tery
    -0.28
    åĮĸçļĦ
    -0.27
    ié
    -0.26
    r
    -0.26
    ×ķ
    -0.26
    ductive
    -0.26
    asic
    -0.25
    POSITIVE LOGITS
    LOPT
    0.25
    _profiles
    0.25
    æĮ¨
    0.25
    mann
    0.24
    fried
    0.24
    orman
    0.24
    heed
    0.24
    profiles
    0.23
    midt
    0.23
    halb
    0.23
    Activations Density 0.050%

    No Known Activations