© 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. 88513
    Prev
    Next
    INDEX
    Explanations

    Software licensing/notices

    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
     opt
    -0.26
    åijĬ
    -0.26
    æī§æ³ķ
    -0.26
    èīĺ
    -0.25
    ç³»
    -0.25
    F
    -0.25
    ch
    -0.24
    li
    -0.24
    æĮĤ
    -0.24
    (en
    -0.24
    POSITIVE LOGITS
     ;↵↵↵
    0.25
    edException
    0.25
     Libre
    0.24
    çķĻä½ı
    0.24
    неÑģÑĤи
    0.24
     rtl
    0.24
     wonders
    0.24
    ARRY
    0.24
    ÐĺÐĿ
    0.23
     refuses
    0.23
    Activations Density 0.002%

    No Known Activations