© 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. 111849
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    æĮijæĪĺ
    -0.26
    race
    -0.25
    æ®ĸ
    -0.24
    oir
    -0.24
    oidal
    -0.24
    éĻ¶
    -0.24
    åĨ²åĩ»
    -0.23
    ByteArray
    -0.23
    onomy
    -0.23
     chù
    -0.23
    POSITIVE LOGITS
     begging
    0.27
    +xml
    0.26
    åįģ足
    0.26
    leccion
    0.23
    beg
    0.23
    longrightarrow
    0.23
     FEMA
    0.22
    ppers
    0.22
     conf
    0.22
    igh
    0.22
    Activations Density 0.000%

    No Known Activations