© 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. 98975
    Prev
    Next
    INDEX
    Explanations

    file downloading and archives

    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°Ħ
    -0.28
     vis
    -0.27
    виз
    -0.27
    è®°å¿Ĩ
    -0.26
     conj
    -0.26
    è§Ĩè§ī
    -0.25
     visual
    -0.25
    _executor
    -0.25
    conj
    -0.25
    .MenuStrip
    -0.24
    POSITIVE LOGITS
    ä¸ĭè½½
    0.43
     download
    0.40
     downloaded
    0.40
    Downloading
    0.40
     DOWNLOAD
    0.39
    .download
    0.37
    download
    0.36
     downloads
    0.36
    Download
    0.36
     Download
    0.36
    Activations Density 0.059%

    No Known Activations