© 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. 20-TRANSCODER-HP
    7. 63759
    Prev
    Next
    INDEX
    Explanations

    where

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adem
    -0.29
    except
    -0.27
    üp
    -0.26
    éĢĭ
    -0.26
    PING
    -0.26
    å§ij
    -0.26
    éĻ¤éĿŀ
    -0.25
    rans
    -0.25
    damage
    -0.24
    INCT
    -0.24
    POSITIVE LOGITS
    oggle
    0.27
     CLR
    0.26
     organizer
    0.26
     glu
    0.25
    å£ķ
    0.25
    aring
    0.24
    OWL
    0.24
     unborn
    0.24
     enumerable
    0.23
     "^
    0.23
    Activations Density 29.967%

    No Known Activations