© 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. 57001
    Prev
    Next
    INDEX
    Explanations

    uses, applications, areas

    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
    磩éĺµ
    -0.27
     æŀ
    -0.26
    _MODULE
    -0.26
    opor
    -0.26
    tracts
    -0.26
    remainder
    -0.26
     Riv
    -0.25
    igsaw
    -0.25
    ryo
    -0.24
     Prot
    -0.24
    POSITIVE LOGITS
     abilities
    0.29
    æľīçĽĬ
    0.28
    comings
    0.27
     applications
    0.27
     adamant
    0.27
    æ°ª
    0.25
     hữu
    0.25
    fitness
    0.25
    ä¸ļ绩
    0.25
    è¿ĶåĽŀæIJľçĭIJ
    0.25
    Activations Density 0.002%

    No Known Activations