© 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. 98013
    Prev
    Next
    INDEX
    Explanations

    province

    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
     ÑģÑĭ
    -0.27
    ahr
    -0.26
    rix
    -0.26
     tuyên
    -0.26
    refer
    -0.26
    contro
    -0.25
    abr
    -0.24
    ened
    -0.24
    .pointer
    -0.24
    thed
    -0.24
    POSITIVE LOGITS
    -wide
    0.31
    pane
    0.29
     rep
    0.29
     borders
    0.27
     sequence
    0.25
     Pang
    0.24
     weighted
    0.24
     d
    0.23
    hel
    0.23
    ental
    0.23
    Activations Density 0.125%

    No Known Activations