© 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. 25071
    Prev
    Next
    INDEX
    Explanations

    san

    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
     bites
    -0.29
    TAIL
    -0.28
    èľļ
    -0.26
    客人
    -0.26
    @c
    -0.25
    ersion
    -0.25
    ploy
    -0.25
    ä¸Ģå¹ķ
    -0.25
    Violation
    -0.25
     Guests
    -0.25
    POSITIVE LOGITS
    æĶ¿çŃĸ
    0.28
    æīĵãģ¡
    0.27
    ti
    0.27
    å¼ĢäºĨ
    0.26
    TestFixture
    0.25
    åįł
    0.24
     Rockefeller
    0.24
    å®£ä¼ł
    0.24
    ç§į
    0.24
     Progress
    0.24
    Activations Density 0.001%

    No Known Activations