© 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. 57915
    Prev
    Next
    INDEX
    Explanations

    bones and joints

    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
     harassing
    -0.29
    åij¨åĪĬ
    -0.27
     propagated
    -0.25
    oron
    -0.25
     invitations
    -0.25
     Counter
    -0.25
    ä¹ĭä½Ļ
    -0.24
    æ³ķå®ļ
    -0.24
     recursively
    -0.23
     doubted
    -0.23
    POSITIVE LOGITS
    -boot
    0.30
    ç¿»
    0.28
    VR
    0.25
    æĮĩæķ°
    0.25
    ials
    0.25
    èħ¿
    0.25
     Wol
    0.25
    éĢī项
    0.25
    urt
    0.25
    WindowSize
    0.24
    Activations Density 0.005%

    No Known Activations