© 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. 97903
    Prev
    Next
    INDEX
    Explanations

    code, documentation

    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
    ardi
    -0.26
    heiten
    -0.26
     stranded
    -0.26
    pios
    -0.25
    @endsection
    -0.25
    太大
    -0.24
     deco
    -0.24
    å®ĩ
    -0.24
    ä¸ºè¿Ľä¸ĢæŃ¥
    -0.23
    çī¹æ´¾
    -0.23
    POSITIVE LOGITS
    clared
    0.29
    åľ¨åĵªéĩĮ
    0.28
    æī¾åĪ°
    0.28
     verbally
    0.28
     labeled
    0.28
    lee
    0.27
    encent
    0.27
    æŁ¥æī¾
    0.26
    stab
    0.26
     MCS
    0.26
    Activations Density 0.012%

    No Known Activations