© 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. 27-TRANSCODER-HP
    7. 57626
    Prev
    Next
    INDEX
    Explanations

    %

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åİŁåĽłä¹ĭä¸Ģ
    -0.29
    coni
    -0.26
     latter
    -0.25
    Broadcast
    -0.25
    æĭ¬
    -0.24
    obar
    -0.23
    ropri
    -0.23
    ificant
    -0.23
    .fc
    -0.23
    ator
    -0.22
    POSITIVE LOGITS
    ful
    0.27
    ponsive
    0.25
    fully
    0.25
    Ùĥا
    0.24
    æŀ¶
    0.24
    Urls
    0.23
    æ°ĽåĽ´
    0.23
    ORM
    0.23
    纵横
    0.23
    alam
    0.22
    Activations Density 0.070%

    No Known Activations