© 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. 87798
    Prev
    Next
    INDEX
    Explanations

    Technical terms

    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
    inent
    -0.30
     Barr
    -0.28
     customs
    -0.27
    ailable
    -0.26
    é»ı
    -0.26
    «ĺ
    -0.24
    -sn
    -0.24
     example
    -0.23
     junior
    -0.23
    è¶ħé«ĺ
    -0.23
    POSITIVE LOGITS
    onian
    0.26
     doubling
    0.24
    vent
    0.24
    zej
    0.23
    _exchange
    0.23
    çijľä¼½
    0.23
    çIJ¥
    0.22
    rud
    0.22
    deck
    0.22
    lit
    0.22
    Activations Density 0.009%

    No Known Activations