© 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. 24017
    Prev
    Next
    INDEX
    Explanations

    ache

    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
     fout
    -0.26
    åij³
    -0.25
    Ĺı
    -0.25
    ÑĤиÑĢов
    -0.24
     Kb
    -0.24
    temps
    -0.24
    Äĩi
    -0.24
    ìĭ
    -0.24
    款
    -0.23
    ailer
    -0.23
    POSITIVE LOGITS
    ento
    0.30
     enclosing
    0.26
    ä¸įç¡®å®ļ
    0.25
    æ°ijæĶ¿
    0.25
    è¯Ħ审
    0.25
    fork
    0.24
    andles
    0.24
     collaps
    0.23
    o
    0.23
    éĴŃ
    0.23
    Activations Density 0.071%

    No Known Activations