© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 111149
    Prev
    Next
    INDEX
    Explanations

    portable

    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
    Negative Logits
    enet
    -0.30
    1
    -0.28
     relatively
    -0.26
    åı¨
    -0.26
    Inf
    -0.25
    }
    -0.24
    ful
    -0.24
    infra
    -0.23
    place
    -0.23
    fluence
    -0.23
    POSITIVE LOGITS
    etsk
    0.30
    NESS
    0.27
    ampil
    0.26
    å·¥ä½ľæĸ¹æ¡Ī
    0.25
    个交æĺĵ
    0.25
    åĬłç´§
    0.25
    åĻ«
    0.24
    åı¯è¾¾
    0.24
    è¿ĻäºĽéĹ®é¢ĺ
    0.24
     aque
    0.24
    Activations Density 0.066%

    No Known Activations