© 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. 57140
    Prev
    Next
    INDEX
    Explanations

    varied topics

    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
     Harvard
    -0.58
    åĵĪä½Ľ
    -0.53
     Yale
    -0.53
     Oxford
    -0.50
    åĮĹ大
    -0.47
     MIT
    -0.46
     Ivy
    -0.46
    MIT
    -0.45
     Stanford
    -0.45
     Cambridge
    -0.44
    POSITIVE LOGITS
    `=
    0.27
    ä¸ĩæĪ·
    0.26
    çĶľç¾İ
    0.26
     Marriott
    0.25
    Ñīен
    0.25
    ä¹°
    0.25
     Composer
    0.24
    hlen
    0.24
    llib
    0.24
    émon
    0.24
    Activations Density 0.024%

    No Known Activations