© 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. 112758
    Prev
    Next
    INDEX
    Explanations

    experiment

    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
    tractive
    -0.27
    éļĨ
    -0.26
    Ĥ¨
    -0.25
    theless
    -0.25
    ibi
    -0.25
    ests
    -0.25
     pedestal
    -0.24
    ihn
    -0.24
     sling
    -0.24
    bis
    -0.24
    POSITIVE LOGITS
    éĺĶ
    0.28
    廿
    0.27
    _CONFIGURATION
    0.26
     ÑģÑĢедÑģÑĤва
    0.24
     with
    0.24
    Coverage
    0.23
     networks
    0.23
     math
    0.23
    etwork
    0.23
    讲æķħäºĭ
    0.23
    Activations Density 0.026%

    No Known Activations