© 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. 130204
    Prev
    Next
    INDEX
    Explanations

    common words

    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
    íĮ©
    -0.28
    ask
    -0.27
     pass
    -0.26
    arium
    -0.26
    Pas
    -0.26
     passed
    -0.26
    arend
    -0.25
    -push
    -0.25
    èĥĮåIJİçļĦ
    -0.24
    ole
    -0.24
    POSITIVE LOGITS
    满æĦı度
    0.28
    æķij
    0.26
    èĩªå¦Ĥ
    0.25
     ern
    0.24
    åIJĥåĪ°
    0.24
     DatabaseReference
    0.23
    gest
    0.23
    UNICATION
    0.23
    ertia
    0.23
    '>č↵
    0.23
    Activations Density 0.004%

    No Known Activations