© 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. 87229
    Prev
    Next
    INDEX
    Explanations

    String manipulation and conditionals

    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
    çĽĴ
    -0.34
    box
    -0.29
    Box
    -0.28
    geh
    -0.27
    hya
    -0.26
    éĢļ
    -0.26
    dis
    -0.25
    认è¯ĨåĪ°
    -0.25
    追
    -0.25
    úde
    -0.25
    POSITIVE LOGITS
    tees
    0.29
    ogne
    0.28
    åĬ¨å·¥
    0.26
    ossed
    0.26
    +E
    0.26
    æĹ©æĻļ
    0.25
    cratch
    0.24
     dru
    0.24
    å·²ä¹ħ
    0.24
    æķij人
    0.23
    Activations Density 0.008%

    No Known Activations