© 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. 142252
    Prev
    Next
    INDEX
    Explanations

    not

    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
     separately
    -0.26
    ynet
    -0.25
    cba
    -0.24
     variations
    -0.24
     fore
    -0.24
     weekdays
    -0.24
     redeem
    -0.23
    çĶµåŃIJéĤ®ä»¶
    -0.23
    icz
    -0.23
    CAF
    -0.23
    POSITIVE LOGITS
    eec
    0.26
     ÃĶ
    0.26
    ç»ĥ
    0.26
    atory
    0.25
    ixe
    0.24
    OLVE
    0.24
    Or
    0.24
    ix
    0.24
     urging
    0.24
    би
    0.23
    Activations Density 1.842%

    No Known Activations