© 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. 130087
    Prev
    Next
    INDEX
    Explanations

    Code/package declarations

    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
    ãĥģãĥ¥
    -0.29
    èĥ½åIJ¦
    -0.27
    ollar
    -0.27
    _READONLY
    -0.27
    WISE
    -0.26
    åľ°æ®µ
    -0.26
    ude
    -0.25
    .destroy
    -0.24
     chế
    -0.24
    wise
    -0.24
    POSITIVE LOGITS
    çĬĢ
    0.29
    _soft
    0.28
     fully
    0.26
    éĿŀ常好
    0.26
    åĪĨç±»
    0.25
    åĽ½å®¶éĺŁ
    0.25
     Fully
    0.24
    _pdu
    0.24
    å½ĴæĿ¥
    0.24
    Fully
    0.24
    Activations Density 0.001%

    No Known Activations