© 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. 57471
    Prev
    Next
    INDEX
    Explanations

    say "Drug"

    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
    iker
    -0.26
    .dom
    -0.26
    ingers
    -0.26
     stir
    -0.25
    à¸Ńาย
    -0.25
    ãĤ¸ãĥ§
    -0.25
    osaic
    -0.25
    igel
    -0.25
    anke
    -0.25
     speakers
    -0.24
    POSITIVE LOGITS
    ivated
    0.26
    eus
    0.25
    æľ¬ç½ij
    0.25
     fırsat
    0.24
    cona
    0.24
    å¸ij
    0.24
     bạc
    0.24
    lyph
    0.24
    (hist
    0.24
    _REGS
    0.24
    Activations Density 0.003%

    No Known Activations