© 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. 88127
    Prev
    Next
    INDEX
    Explanations

    Gathering

    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
    è®°èĢħéĩĩ访
    -0.28
    adesh
    -0.28
    apolis
    -0.27
    (es
    -0.27
    sters
    -0.27
    adel
    -0.25
     Gamb
    -0.25
    软
    -0.25
    entially
    -0.25
    åīįèĢħ
    -0.25
    POSITIVE LOGITS
    éľ²
    0.28
    è¦ģ好好
    0.27
    æĿµ
    0.25
     commun
    0.24
    æľīéĻIJ
    0.24
    _sur
    0.23
    ä¹ŁåºĶ该
    0.23
     inv
    0.23
     trough
    0.23
     priv
    0.23
    Activations Density 0.007%

    No Known Activations