© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 131228
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    Negative Logits
    rete
    -0.27
    /Instruction
    -0.26
    urses
    -0.26
    è£ħ
    -0.25
     Protest
    -0.25
     Lowe
    -0.24
     description
    -0.24
     δ
    -0.24
    emble
    -0.24
    errupt
    -0.24
    POSITIVE LOGITS
    è¿ĻäºĽäºº
    0.30
    оÑĩнÑĭй
    0.26
    è¿ĻäºĽä¸ľè¥¿
    0.25
    åĶ¿
    0.25
    çħ
    0.25
    Inv
    0.24
    лоÑģÑĮ
    0.24
    è¿Ļåľº
    0.24
    itm
    0.24
    FIX
    0.24
    Activations Density 0.001%

    No Known Activations