© 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. 112358
    Prev
    Next
    INDEX
    Explanations

    Writing, code, instructions

    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
    ä¸Ģè§Ĵ
    -0.26
    __('
    -0.25
    æı©
    -0.25
     gig
    -0.25
    èĩªç§°
    -0.24
     hurl
    -0.23
    积水
    -0.23
     Needless
    -0.23
    çļĦæķ°éĩı
    -0.23
    åĸĬ
    -0.23
    POSITIVE LOGITS
    bbe
    0.30
    beth
    0.28
    为ä½ķ
    0.27
    uted
    0.26
    è§ĤçĤ¹
    0.25
    abar
    0.25
    -blog
    0.24
    çŃĸ
    0.24
    å¹³
    0.24
     NTN
    0.24
    Activations Density 0.014%

    No Known Activations