© 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. 58165
    Prev
    Next
    INDEX
    Explanations

    trace

    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
    sWith
    -0.37
    ty
    -0.29
    rest
    -0.28
    TING
    -0.27
    éªļ
    -0.27
    rey
    -0.26
    service
    -0.25
    thus
    -0.24
    æľįåĬ¡ä¸ļ
    -0.24
    åĬŁè¯¾
    -0.24
    POSITIVE LOGITS
    åĴĮæĶ¯æĮģ
    0.29
    cen
    0.29
    worthy
    0.27
    主治
    0.26
    cid
    0.25
    geber
    0.24
    寮
    0.23
    intl
    0.23
    å¯Įæ°ij
    0.23
    eland
    0.23
    Activations Density 0.047%

    No Known Activations