© 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. 129615
    Prev
    Next
    INDEX
    Explanations

    Research/scientific writing

    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
    oir
    -0.28
    inati
    -0.26
    /me
    -0.26
    宿
    -0.26
    ME
    -0.25
    ikit
    -0.25
     Me
    -0.25
    åIJŁ
    -0.25
    itus
    -0.24
    å¯ĦãģĽ
    -0.24
    POSITIVE LOGITS
    ))-
    0.25
    AAF
    0.24
    hões
    0.24
    alue
    0.23
    并äºİ
    0.23
    éľħ
    0.23
    æ¯ķä¸ļåIJİ
    0.23
    shal
    0.23
    竽
    0.23
     spl
    0.22
    Activations Density 0.010%

    No Known Activations