© 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. 97670
    Prev
    Next
    INDEX
    Explanations

    tumors and blasts

    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
    åij·
    -0.27
    akit
    -0.25
    estate
    -0.25
    thing
    -0.25
    ç§Łè½¦
    -0.25
    äºĨä¸Ģ声
    -0.24
    istrator
    -0.24
    bau
    -0.24
    alta
    -0.24
    ystick
    -0.24
    POSITIVE LOGITS
    ural
    0.29
    urf
    0.28
    rophe
    0.27
    ão
    0.27
    رد
    0.26
    pread
    0.26
    s
    0.26
    Closure
    0.26
    scale
    0.25
    reme
    0.25
    Activations Density 0.138%

    No Known Activations