© 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. 87847
    Prev
    Next
    INDEX
    Explanations

    :

    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
    processable
    -0.26
    ç¨ĭ
    -0.25
    ^K
    -0.25
    icc
    -0.24
     inexperienced
    -0.24
     peak
    -0.24
     seeded
    -0.24
    管çIJĨä½ĵåĪ¶
    -0.24
     initState
    -0.23
    uvw
    -0.23
    POSITIVE LOGITS
    åĢĴ
    0.29
    迹
    0.29
    åĪ°å¤Ħ
    0.29
    клад
    0.28
    January
    0.26
     February
    0.26
    ÈĻ
    0.26
    May
    0.25
    aving
    0.25
     January
    0.25
    Activations Density 0.117%

    No Known Activations