© 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. 87501
    Prev
    Next
    INDEX
    Explanations

    data processing

    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
     di
    -0.30
    ys
    -0.27
    quo
    -0.26
    çļĦæ¯Ķä¾ĭ
    -0.25
    å¹³åı°ä¸Ĭ
    -0.25
     kinky
    -0.24
     proportion
    -0.24
    åľ¨æĦı
    -0.24
    ç»ĵæŀľæĺ¾ç¤º
    -0.24
     nucle
    -0.24
    POSITIVE LOGITS
    shaw
    0.28
     Conduct
    0.28
     Kind
    0.27
    egin
    0.27
    ang
    0.27
    _KIND
    0.26
    covering
    0.26
    YA
    0.26
    engers
    0.26
    Ø£Ùħ
    0.26
    Activations Density 0.030%

    No Known Activations