© 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. 24387
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    ä¸ĢèĦļ
    -0.30
    KP
    -0.26
    å¤ļä¹ħ
    -0.26
    itung
    -0.26
    หาà¸ģ
    -0.25
    **č↵
    -0.25
    (Column
    -0.25
     defs
    -0.24
    漫
    -0.24
    à¹īม
    -0.24
    POSITIVE LOGITS
    é¡·
    0.27
     fert
    0.25
    attles
    0.25
    powered
    0.24
     fidelity
    0.24
    eker
    0.24
    æ½Ľ
    0.24
    ossa
    0.23
    capacity
    0.23
     capacity
    0.23
    Activations Density 0.004%

    No Known Activations