© 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. 23937
    Prev
    Next
    INDEX
    Explanations

    to

    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
    &_
    -0.32
    &q
    -0.30
     Necklace
    -0.27
    &r
    -0.26
     wa
    -0.26
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.25
    离ä¸įå¼Ģ
    -0.24
    çľĭçĤ¹
    -0.24
    fol
    -0.24
    essler
    -0.23
    POSITIVE LOGITS
    \"]
    0.28
    ategies
    0.26
    -stage
    0.26
     Elm
    0.26
    rote
    0.26
    çĻ»ä¸Ĭ
    0.26
    就好äºĨ
    0.25
    éķ¿çĽ¸
    0.25
    UF
    0.24
    ION
    0.24
    Activations Density 0.011%

    No Known Activations