© 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. 87547
    Prev
    Next
    INDEX
    Explanations

    Negative or undesirable events

    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
    次
    -0.30
    urai
    -0.28
    mai
    -0.27
    ix
    -0.26
    å±Ĥ
    -0.26
    меÑģ
    -0.24
    ä»ĵ
    -0.24
    ç¨Ģ
    -0.24
     myself
    -0.24
     ourselves
    -0.24
    POSITIVE LOGITS
    exo
    0.27
    ottes
    0.25
    erness
    0.24
    æ¬
    0.23
    aden
    0.23
    eração
    0.23
    /string
    0.23
    _corpus
    0.22
    /Set
    0.22
    InstanceId
    0.22
    Activations Density 0.019%

    No Known Activations