© 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. 87472
    Prev
    Next
    INDEX
    Explanations

    Now

    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
    ropri
    -0.32
    ogui
    -0.29
    essed
    -0.28
    ses
    -0.27
    deer
    -0.25
    ycin
    -0.24
    etcode
    -0.23
     그리
    -0.23
     sud
    -0.23
    åĴĮ个人
    -0.23
    POSITIVE LOGITS
     however
    0.28
     unheard
    0.25
    åij¢
    0.25
    æĹ©çĤ¹
    0.24
     there
    0.24
    abe
    0.24
    ACA
    0.24
    Fac
    0.24
    uble
    0.24
    boo
    0.23
    Activations Density 0.014%

    No Known Activations