© 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. 87741
    Prev
    Next
    INDEX
    Explanations

    bacterial

    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
    ogg
    -0.28
    onn
    -0.27
    og
    -0.27
    ewidth
    -0.25
    haul
    -0.24
    è·Ĺ
    -0.24
    icing
    -0.24
    azz
    -0.23
    apos
    -0.23
    standing
    -0.23
    POSITIVE LOGITS
     disc
    0.29
    disc
    0.27
    è¹Ħ
    0.26
    对人ä½ĵ
    0.25
    bara
    0.25
    Disc
    0.25
     cere
    0.24
     discs
    0.24
     towel
    0.24
    身ä½ĵ
    0.24
    Activations Density 0.109%

    No Known Activations