© 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. 88555
    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
    plr
    -0.30
    æįŁå®³
    -0.27
     legitimately
    -0.26
    å®ļä¹ī
    -0.25
    Mag
    -0.24
    DIC
    -0.24
     alm
    -0.24
    æŀĦ
    -0.24
    xFFFFFFFF
    -0.24
    è§ģéĿ¢
    -0.24
    POSITIVE LOGITS
    宽
    0.27
     heights
    0.25
     pros
    0.25
     css
    0.25
     billions
    0.25
    èIJ¥
    0.25
    è¶Ĭæĺ¯
    0.25
    зв
    0.24
    æĶ¾å®½
    0.24
    >{@
    0.24
    Activations Density 0.182%

    No Known Activations

    This feature has no known activations.