© 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. 9114
    Prev
    Next
    INDEX
    Explanations

    Website or document extraction

    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
     sponsoring
    -0.27
    空æ°Ķ
    -0.26
    /New
    -0.26
    缴åįĩæľº
    -0.26
     Par
    -0.25
     offic
    -0.25
     sponsorship
    -0.25
    HostName
    -0.25
     Wonderland
    -0.25
    _Connection
    -0.24
    POSITIVE LOGITS
    ernal
    0.32
    HB
    0.28
    åĽŀäºĭ
    0.28
    antine
    0.26
    ource
    0.26
    erno
    0.26
    semble
    0.25
    htable
    0.25
    ãģ¨ãĤĤ
    0.25
    æ¯ı次éĥ½
    0.25
    Activations Density 0.009%

    No Known Activations