© 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. 130155
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     thiá»ĩu
    -0.25
    -earth
    -0.25
    Frameworks
    -0.25
    еждÑĥ
    -0.25
     Leather
    -0.25
    plete
    -0.24
     Grinder
    -0.24
    chemy
    -0.24
    arna
    -0.23
    ÅĽli
    -0.23
    POSITIVE LOGITS
    moth
    0.29
     OFF
    0.28
    anes
    0.28
    åĬŀåħ¬å®¤
    0.26
     unions
    0.25
    ningen
    0.25
     catch
    0.25
    chas
    0.25
    UIS
    0.25
    >Action
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.