© 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. 32-TRANSCODER-HP
    7. 42860
    Prev
    Next
    INDEX
    Explanations

    periodic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Match
    -0.28
    çªĹå¤ĸ
    -0.27
     Orig
    -0.26
    specs
    -0.25
    oppers
    -0.25
    å¾Īæ·±
    -0.25
     Zodiac
    -0.25
    offs
    -0.24
     Labs
    -0.24
     Exceptions
    -0.24
    POSITIVE LOGITS
    ally
    0.40
    ity
    0.35
    ality
    0.32
    ALLY
    0.30
    aly
    0.30
    ating
    0.29
    idade
    0.29
    ale
    0.29
    èħ°
    0.28
    ation
    0.28
    Activations Density 0.003%

    No Known Activations