© 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. 24692
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    -Mobile
    -0.28
    monds
    -0.26
     pushed
    -0.25
    éĻ¤æѤä¹ĭå¤ĸ
    -0.25
    GN
    -0.25
    ernational
    -0.24
    弯
    -0.24
    ä¸į对
    -0.24
    æѤ
    -0.24
    .getNext
    -0.23
    POSITIVE LOGITS
    guess
    0.25
     usu
    0.25
    ivar
    0.24
    ä¾Ĺ
    0.24
    _charge
    0.24
    åħĥå®Ŀ
    0.24
     Sapphire
    0.24
     Budd
    0.24
     veg
    0.24
    èĵĿ
    0.23
    Activations Density 0.028%

    No Known Activations