© 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. 8203
    Prev
    Next
    INDEX
    Explanations

    of

    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
    æŃ¤äºº
    -0.30
    åĪ»
    -0.28
    è¡Ķ
    -0.28
     wholes
    -0.27
    大çĽĺ
    -0.27
    ç¯Ĩ
    -0.26
    ict
    -0.26
    ometrics
    -0.25
     contested
    -0.25
    æīĺ
    -0.25
    POSITIVE LOGITS
    ãĥĭãĥ³ãĤ°
    0.28
    unar
    0.26
    ,âĢ¦↵↵
    0.26
    _CUBE
    0.25
    _TB
    0.25
    大å®Ĺ
    0.24
    arsers
    0.24
    âĨĻ
    0.24
    /GPL
    0.24
    å´ĩ
    0.24
    Activations Density 0.001%

    No Known Activations