© 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. 24868
    Prev
    Next
    INDEX
    Explanations

    among

    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
    urf
    -0.27
     iter
    -0.27
    iterated
    -0.26
    ä¸įå¿į
    -0.26
    oze
    -0.26
    å·¡æŁ¥
    -0.25
    家éķ¿ä»¬
    -0.25
     Iter
    -0.24
     tamaño
    -0.24
    olvers
    -0.24
    POSITIVE LOGITS
    nu
    0.31
    ="?
    0.26
     essential
    0.26
     crucial
    0.26
     dream
    0.26
     external
    0.25
     studies
    0.25
     assim
    0.25
     property
    0.25
     impacts
    0.25
    Activations Density 0.009%

    No Known Activations