© 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. 98908
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    éĤ£ä¹Īç®Ģåįķ
    -0.26
    ritch
    -0.25
    avel
    -0.25
    æIJŀå®ļ
    -0.24
    ëĬĶëį°
    -0.24
    鼶è·Ŀ离
    -0.24
     bad
    -0.24
    æĶ»åĿļ
    -0.24
    errick
    -0.24
     solidity
    -0.24
    POSITIVE LOGITS
     please
    0.36
     consultation
    0.35
     Please
    0.34
    Please
    0.32
     consult
    0.32
    æķ¬è¯·
    0.31
    .Please
    0.31
    请
    0.30
    请æĤ¨
    0.29
    please
    0.28
    Activations Density 0.005%

    No Known Activations