© 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. 98480
    Prev
    Next
    INDEX
    Explanations

    code, projects, studies

    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
    alem
    -0.28
    alsy
    -0.28
    åħĥå·¦åı³
    -0.24
     lifts
    -0.24
     epis
    -0.23
    sPid
    -0.23
     pilot
    -0.23
     oran
    -0.23
    arna
    -0.23
    bilt
    -0.23
    POSITIVE LOGITS
     Opening
    0.24
     moreover
    0.24
    æѤç§į
    0.24
     furthermore
    0.24
    things
    0.24
     totally
    0.23
    举
    0.23
     corres
    0.23
    缸å½ĵ
    0.23
    ;<
    0.23
    Activations Density 0.000%

    No Known Activations