© 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. 97520
    Prev
    Next
    INDEX
    Explanations

    .

    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
    åĶ¾
    -0.26
    _follow
    -0.25
    .follow
    -0.25
     kosher
    -0.25
    dirty
    -0.24
    ansson
    -0.24
     pudding
    -0.24
    åĴĦ
    -0.24
    quila
    -0.24
    panion
    -0.23
    POSITIVE LOGITS
     Maj
    0.28
    otes
    0.27
    abol
    0.26
    abaj
    0.26
    ÅĤo
    0.25
    红æĺŁ
    0.25
    awai
    0.25
    bear
    0.24
    reso
    0.24
    èĥļ
    0.23
    Activations Density 0.001%

    No Known Activations