© 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. 24463
    Prev
    Next
    INDEX
    Explanations

    .

    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
    ktor
    -0.28
    ẩu
    -0.27
    è¶³å¤Ł
    -0.26
    棵æłij
    -0.25
     discipline
    -0.25
    ä½ķåĨµ
    -0.24
    è¶³å¤ŁçļĦ
    -0.24
    æIJIJ
    -0.24
    çºĮ
    -0.24
    ivec
    -0.24
    POSITIVE LOGITS
     each
    0.36
     Each
    0.36
    Each
    0.34
     drawer
    0.33
     The
    0.32
    ://
    0.31
    kit
    0.30
    The
    0.30
     for
    0.29
    第ä¸Ģ次
    0.29
    Activations Density 0.005%

    No Known Activations