© 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. 97748
    Prev
    Next
    INDEX
    Explanations

    Common words/symbols

    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
    agraph
    -0.34
    avity
    -0.31
    AFF
    -0.29
    æ¯ħçĦ¶
    -0.29
    aff
    -0.27
    Aff
    -0.26
    -aff
    -0.26
    af
    -0.26
    metic
    -0.26
    chnitt
    -0.25
    POSITIVE LOGITS
    oub
    0.27
    çĨĺ
    0.25
    åľ¨å½ĵåľ°
    0.25
    éĺ¿éĩĮ
    0.25
    åįĩ温
    0.24
    _cod
    0.23
    igor
    0.23
     ge
    0.23
    _ib
    0.23
    iert
    0.23
    Activations Density 0.031%

    No Known Activations