© 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. 111344
    Prev
    Next
    INDEX
    Explanations

    by, from, at

    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
    å·¥å§Ķ
    -0.26
    fest
    -0.26
    ãĤ»ãĥĥãĥĪ
    -0.25
     INC
    -0.25
    -gnu
    -0.25
     FindObjectOfType
    -0.23
    young
    -0.23
    /YYYY
    -0.23
    è°³
    -0.23
    utenberg
    -0.23
    POSITIVE LOGITS
    OLA
    0.28
    ailer
    0.26
    _backward
    0.26
    çĽİ
    0.26
     íĺ¸
    0.26
    åŃ£
    0.26
    åŁĥå°Ķ
    0.25
    åħ°
    0.24
    åİĮ
    0.24
    vard
    0.24
    Activations Density 0.031%

    No Known Activations