© 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. 87460
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    åı¦ä¸Ģç§į
    -0.27
    s
    -0.26
    éĺŁä¼į
    -0.26
    èĢĮåĩº
    -0.26
     sÆ°
    -0.26
    +_
    -0.25
    sar
    -0.25
    oyo
    -0.25
    åij²
    -0.25
    blog
    -0.25
    POSITIVE LOGITS
     dead
    0.26
    waters
    0.26
    >")
    0.25
    (dead
    0.24
     Howe
    0.24
    æĥ³åİ»
    0.24
    å¿»
    0.24
    迦
    0.24
    _GO
    0.24
     arms
    0.23
    Activations Density 0.058%

    No Known Activations