© 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. 23-TRANSCODER-HP
    7. 25122
    Prev
    Next
    INDEX
    Explanations

    know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å°½åĬĽ
    -0.26
     opción
    -0.26
    ay
    -0.26
    Ùĩر
    -0.26
    VEL
    -0.26
     Daw
    -0.26
     stresses
    -0.25
    urge
    -0.25
    åħĭ
    -0.25
     strings
    -0.25
    POSITIVE LOGITS
    æĢ§åij½
    0.28
    å¦ĥ
    0.26
    ually
    0.26
     ambiguous
    0.26
    æīĭåĬ¨
    0.26
    irsch
    0.25
    utors
    0.24
    arda
    0.24
    chaft
    0.24
    ully
    0.24
    Activations Density 0.043%

    No Known Activations