© 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. 9177
    Prev
    Next
    INDEX
    Explanations

    objects

    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
    纪å¾ĭ
    -0.36
    è°ĥåīĤ
    -0.27
    èĩªå¾ĭ
    -0.27
    _deep
    -0.26
    润æ»ij
    -0.26
    æ±ĭ
    -0.25
    æµģæ·Į
    -0.25
    賦
    -0.25
    è§Ĵèī²
    -0.25
    fund
    -0.24
    POSITIVE LOGITS
    对象
    0.32
     objects
    0.31
     object
    0.31
    object
    0.29
    obj
    0.29
    cases
    0.29
    objects
    0.28
     пÑĢедмеÑĤ
    0.28
    GetObject
    0.28
    Objects
    0.27
    Activations Density 0.000%

    No Known Activations