© 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. 112632
    Prev
    Next
    INDEX
    Explanations

    Code and software development

    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
    theid
    -0.26
    bate
    -0.24
     guilty
    -0.24
    åı®
    -0.24
     stocking
    -0.23
    bef
    -0.23
    弧
    -0.23
     picnic
    -0.23
     Pc
    -0.23
     apolog
    -0.23
    POSITIVE LOGITS
    ustum
    0.30
     prelim
    0.28
    äºĨä¸Ģåı£
    0.28
    oleon
    0.26
    (Profile
    0.25
    à¸ģรม
    0.24
     /**<
    0.24
    ade
    0.23
    交æĺĵå¹³åı°
    0.23
    istani
    0.23
    Activations Density 0.001%

    No Known Activations