© 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. 27-TRANSCODER-HP
    7. 58237
    Prev
    Next
    INDEX
    Explanations

    important/essential

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ysics
    -0.33
    opoulos
    -0.27
    ields
    -0.27
    çIJĨä¼ļ
    -0.27
    åĪ¶åº¦æĶ¹éĿ©
    -0.25
    odor
    -0.25
    hog
    -0.25
     Conservatives
    -0.24
    ordinates
    -0.24
    ç§ĥ
    -0.24
    POSITIVE LOGITS
    ;
    0.33
     especially
    0.29
     Especially
    0.28
     deleg
    0.28
    ;t
    0.26
     Strom
    0.26
    ;c
    0.26
     plus
    0.26
     simul
    0.25
    #c
    0.25
    Activations Density 0.005%

    No Known Activations