© 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. 129449
    Prev
    Next
    INDEX
    Explanations

    Code and/or technical texts

    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·¨
    -0.25
     Shield
    -0.25
    anic
    -0.24
     oczywiÅĽcie
    -0.24
    jpg
    -0.24
     Giant
    -0.24
    太æŀģ
    -0.24
    itives
    -0.24
    illage
    -0.23
    æ¶İ
    -0.23
    POSITIVE LOGITS
    Exact
    0.28
     exact
    0.27
    exact
    0.25
    owi
    0.25
    æĬľãģij
    0.25
     Bundy
    0.24
     Bor
    0.24
     Serializable
    0.23
    æĬľ
    0.23
    phase
    0.23
    Activations Density 0.052%

    No Known Activations