© 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. 22-TRANSCODER-HP
    7. 130567
    Prev
    Next
    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¾Īæ¸ħæ¥ļ
    -0.29
    å°±æѤ
    -0.25
    isher
    -0.25
    ç§Ģ
    -0.24
    ORG
    -0.24
    éĶĻ
    -0.24
    -interest
    -0.24
    å¸Ī
    -0.24
    çIJĥè¿·
    -0.23
    缸è¾ĥ
    -0.23
    POSITIVE LOGITS
     managed
    0.29
    man
    0.29
    aman
    0.29
    çķĻ
    0.27
    åĨħéĻĨ
    0.26
    etas
    0.26
    iero
    0.26
    etine
    0.25
    ursive
    0.25
    amber
    0.25
    Activations Density 0.014%

    No Known Activations