© 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. 88381
    Prev
    Next
    INDEX
    Explanations

    infection

    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
    å®ĹæŨ
    -0.29
    frm
    -0.28
    iffs
    -0.27
    çī¹çĤ¹
    -0.27
    iff
    -0.25
    haul
    -0.25
    ims
    -0.25
    _accepted
    -0.24
    éĩĩ访
    -0.24
     Fe
    -0.24
    POSITIVE LOGITS
    ettes
    0.27
     +:+
    0.24
    èĵĭ
    0.24
    ustrial
    0.23
    æīĪ
    0.23
    å¾¼
    0.23
     заÑĤ
    0.23
    urette
    0.23
    terior
    0.23
    ossal
    0.23
    Activations Density 0.018%

    No Known Activations