© 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. 107681
    Prev
    Next
    INDEX
    Explanations

    enter

    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
    LoginForm
    -0.27
    å°Ŀ
    -0.27
    ObjectType
    -0.25
    conc
    -0.25
     reflective
    -0.25
    åIJ¬è§ģ
    -0.24
    ç½ķ
    -0.24
    宿è¿ģ
    -0.24
     Dominic
    -0.24
     reflect
    -0.24
    POSITIVE LOGITS
    严
    0.31
     onRequest
    0.26
     shoulders
    0.26
    å°º
    0.25
    èĤ©èĨĢ
    0.25
    æĹĭ
    0.24
    apel
    0.23
    çĶ²
    0.23
    à¸ģระ
    0.23
    (AT
    0.23
    Activations Density 13.748%

    No Known Activations