© 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. 20-TRANSCODER-HP
    7. 107822
    Prev
    Next
    INDEX
    Explanations

    academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ysz
    -0.28
     persist
    -0.27
    éĻª
    -0.26
    Persist
    -0.25
    edException
    -0.25
    åĩłä¹İæīĢæľī
    -0.25
    autor
    -0.25
    bn
    -0.24
     manoe
    -0.24
     thinner
    -0.24
    POSITIVE LOGITS
    æ¥ŀ
    0.29
    rogen
    0.27
     #%
    0.26
     Seed
    0.24
    аÑĤа
    0.24
    ensive
    0.24
    __$
    0.24
    伦
    0.24
    éļĨ
    0.23
    åĬ©æīĭ
    0.23
    Activations Density 35.336%

    No Known Activations