© 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. 24683
    Prev
    Next
    INDEX
    Explanations

    Pronouns

    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
     how
    -0.41
    å¦Ĥä½ķ
    -0.36
    æĢİä¹Ī
    -0.34
     what
    -0.32
    ä½łæĢİä¹Ī
    -0.31
    è¿ĺæľīä»Ģä¹Ī
    -0.30
    为ä»Ģä¹Ī
    -0.30
     How
    -0.29
    ãģ©ãģĨ
    -0.28
    aje
    -0.28
    POSITIVE LOGITS
    elize
    0.27
    ä¸ĢéĹª
    0.26
     Platz
    0.25
     ÑģÑĤоиÑĤ
    0.24
     PublicKey
    0.24
    _MARKER
    0.24
    /stat
    0.24
    _ax
    0.23
    让èĩªå·±
    0.23
    æ´Ľåħĭ
    0.23
    Activations Density 0.007%

    No Known Activations