© 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. 88344
    Prev
    Next
    INDEX
    Explanations

    code instructions/restrictions

    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
    actly
    -0.27
    åij¢
    -0.25
     (£
    -0.25
    å®Įæķ´çļĦ
    -0.25
    ÑĩÑĮ
    -0.23
    éĩįè¦ģä½ľçĶ¨
    -0.23
    ä¸ŃæľŁ
    -0.23
    紧迫
    -0.23
    ä¹İ
    -0.23
    _iterations
    -0.23
    POSITIVE LOGITS
     mo
    0.29
    æ¸ħåįİ
    0.29
    ijľ
    0.27
     den
    0.27
    robe
    0.26
     wrong
    0.26
    odem
    0.25
    åIJį声
    0.24
     cro
    0.24
    icens
    0.24
    Activations Density 0.046%

    No Known Activations