© 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. 97489
    Prev
    Next
    INDEX
    Explanations

    photos

    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¸įéĶĻ
    -0.29
    å¾Ĵ
    -0.27
    ä¸īçĤ¹
    -0.27
    yles
    -0.26
    ITU
    -0.25
    ICLES
    -0.25
    æģķ
    -0.25
    деÑģÑıÑĤ
    -0.25
    ivals
    -0.24
    çī¹éķ¿
    -0.24
    POSITIVE LOGITS
    a
    0.45
    o
    0.28
    e
    0.28
    t
    0.27
    ting
    0.27
    n
    0.26
    ing
    0.26
    aÄŁ
    0.25
    äºĽä»Ģä¹Ī
    0.25
    i
    0.25
    Activations Density 0.108%

    No Known Activations