© 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. 57309
    Prev
    Next
    INDEX
    Explanations

    that

    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
    ÑĩиÑģлен
    -0.27
    dux
    -0.27
    umping
    -0.27
     whistleblower
    -0.26
     Contributor
    -0.25
    _KIND
    -0.25
    anio
    -0.25
    ä¸ĵå±ŀ
    -0.24
    IVEN
    -0.24
    imator
    -0.24
    POSITIVE LOGITS
    æ³ķå¾ĭè§Ħå®ļ
    0.30
    å©Ĩå©Ĩ
    0.29
    å¹²æ¶ī
    0.29
    管çIJĨåijĺ
    0.29
     bathroom
    0.27
    åĨ³çŃĸ
    0.27
    μ
    0.27
    isi
    0.26
    æĶ¿çŃĸ
    0.26
     abstract
    0.26
    Activations Density 0.002%

    No Known Activations