© 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. 57766
    Prev
    Next
    INDEX
    Explanations

    Book metadata and code snippets

    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
    ĵį
    -0.32
    ZX
    -0.28
     verbs
    -0.28
    acus
    -0.27
    ä¸ĩçī©
    -0.26
    [last
    -0.26
     Verb
    -0.25
     alien
    -0.24
    rooms
    -0.24
    è°©
    -0.23
    POSITIVE LOGITS
    oha
    0.30
     nowhere
    0.27
    adro
    0.26
    ModelCreating
    0.25
    length
    0.25
    è°Ĭ
    0.24
    æĶ¶èĹı
    0.24
    lay
    0.24
    \Container
    0.24
     favor
    0.23
    Activations Density 0.021%

    No Known Activations