© 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. 111807
    Prev
    Next
    INDEX
    Explanations

    of

    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
    zin
    -0.31
    èľļ
    -0.25
    çĺµ
    -0.24
    zers
    -0.24
    abad
    -0.24
    å®ŀä¸ļ
    -0.24
    ients
    -0.23
    _DF
    -0.23
     receptions
    -0.23
    ëħIJ
    -0.23
    POSITIVE LOGITS
    salt
    0.26
    .assets
    0.25
    该项
    0.24
    mente
    0.24
    èĥ½è®©
    0.23
    èĥ½å¤Łè®©
    0.23
    éĢļå¾Ģ
    0.23
    _LICENSE
    0.23
    swith
    0.23
    审æī¹
    0.23
    Activations Density 0.022%

    No Known Activations