© 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. 130766
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives

    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
    ãĢģ
    -0.44
    ,
    -0.31
     &
    -0.27
    ä¸Ģ種
    -0.26
    $$$
    -0.25
    &view
    -0.24
    ,...↵
    -0.24
    ãĢģãĢĮ
    -0.24
    .splitext
    -0.24
    åĩ³
    -0.24
    POSITIVE LOGITS
    åħĪ
    0.30
    irit
    0.29
    çİĩ
    0.28
    onis
    0.26
    好
    0.26
    çĥĤ
    0.26
    umo
    0.25
    ir
    0.24
    ALLED
    0.24
    kj
    0.23
    Activations Density 0.031%

    No Known Activations