© 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. 56924
    Prev
    Next
    INDEX
    Explanations

    earn or win

    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
     wholes
    -0.27
     dw
    -0.26
    _seqs
    -0.26
     apro
    -0.25
    lz
    -0.25
    delay
    -0.24
    è¿IJ
    -0.24
    è¶Ĭæĺ¯
    -0.24
    /lic
    -0.24
     sexuality
    -0.24
    POSITIVE LOGITS
    ARB
    0.31
    xab
    0.26
    cxx
    0.26
    xaf
    0.26
    caf
    0.25
    оÑĢдин
    0.25
    AXB
    0.24
    åħ±æĮ¯
    0.24
    uve
    0.24
    acter
    0.24
    Activations Density 0.002%

    No Known Activations