© 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. 9267
    Prev
    Next
    INDEX
    Explanations

    into

    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
    /*@
    -0.30
    HING
    -0.28
    ष
    -0.27
    ç»´å¥ĩ
    -0.26
    icare
    -0.26
    LENGTH
    -0.26
    ·æĸ°
    -0.25
    Ny
    -0.24
    patterns
    -0.24
    éĺ³æĢ§
    -0.24
    POSITIVE LOGITS
     jest
    0.26
    otic
    0.25
     system
    0.25
     fl
    0.25
    case
    0.25
    arness
    0.25
     case
    0.25
    oir
    0.24
     honor
    0.24
     hun
    0.24
    Activations Density 0.003%

    No Known Activations