© 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. 24171
    Prev
    Next
    INDEX
    Explanations

    server

    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
    å¹Į
    -0.30
    agonal
    -0.26
     Casino
    -0.26
    odi
    -0.26
    agon
    -0.26
    AGON
    -0.26
    adian
    -0.25
    ülü
    -0.25
    nesty
    -0.25
    ivism
    -0.24
    POSITIVE LOGITS
    itin
    0.25
    å½ĵå±Ģ
    0.25
    è¿ĩå¤ļ
    0.25
    å¹´åIJİ
    0.25
    åĵĢ
    0.24
    ĽĦ
    0.24
    ruk
    0.24
    ITY
    0.24
    -order
    0.24
    aseline
    0.23
    Activations Density 0.016%

    No Known Activations