© 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. 23-TRANSCODER-HP
    7. 24077
    Prev
    Next
    INDEX
    Explanations

    Code, lyrics, and rentals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ITES
    -0.28
    ä½Ĩæĺ¯åľ¨
    -0.27
    apter
    -0.26
    å°±æĺ¯åľ¨
    -0.26
     Ella
    -0.25
    éĿĴå±±
    -0.25
    åľ¨ä»ĸçļĦ
    -0.25
    CLAIM
    -0.24
    åľ¨è¿Ļ
    -0.24
     automat
    -0.24
    POSITIVE LOGITS
     imaginable
    0.29
    æĥħåĨµè¿Ľè¡Į
    0.29
     AssetImage
    0.29
    ãĥĬãĥ¼
    0.26
     meshes
    0.26
     Unreal
    0.26
    å¿į
    0.25
    _marshall
    0.25
    roof
    0.25
    åı£åij³
    0.24
    Activations Density 0.005%

    No Known Activations