© 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. 35-TRANSCODER-HP
    7. 40046
    Prev
    Next
    INDEX
    Explanations

    Place names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.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¥¥åľ°åĪ©
    -0.29
    åºĶçĶ¨åľºæĻ¯
    -0.27
    åıĺæĢģ
    -0.27
    enticate
    -0.26
    ASCII
    -0.26
    Ĭ¶æĢģ
    -0.26
    èĿ´èĿ¶
    -0.25
    toggle
    -0.25
    èĭ±éķij
    -0.24
    å¼Ģæľº
    -0.24
    POSITIVE LOGITS
    -Cs
    0.41
    -no
    0.39
    -K
    0.38
    -Jun
    0.37
    -k
    0.37
    -Ch
    0.36
    -su
    0.36
    -U
    0.36
    -Z
    0.36
    -Sah
    0.35
    Activations Density 26.064%

    No Known Activations