© 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. 56928
    Prev
    Next
    INDEX
    Explanations

    code commands

    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
    ŀæĢ§
    -0.27
    uyo
    -0.26
    AsyncResult
    -0.24
    allee
    -0.24
    OfYear
    -0.23
    finity
    -0.23
    à¤ŀ
    -0.23
    nullable
    -0.23
    ugal
    -0.23
    å°±è¦ģ
    -0.23
    POSITIVE LOGITS
     applying
    0.50
     clicking
    0.49
     inserting
    0.44
     executing
    0.43
    çĤ¹åĩ»
    0.43
     putting
    0.42
    æīĵå¼Ģ
    0.41
     taking
    0.41
     pressing
    0.41
    ç¿»å¼Ģ
    0.40
    Activations Density 0.007%

    No Known Activations