© 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. 57221
    Prev
    Next
    INDEX
    Explanations

    rest

    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
    éĻIJæŶ
    -0.28
    swers
    -0.27
    è´´
    -0.26
    soever
    -0.26
    esso
    -0.25
    BUM
    -0.25
    anken
    -0.25
    è²¼
    -0.24
     reflections
    -0.24
    igin
    -0.24
    POSITIVE LOGITS
    aurant
    0.37
    elt
    0.32
    lessness
    0.31
    aurants
    0.30
    aur
    0.29
    rooms
    0.29
    less
    0.29
    ive
    0.28
    æĥł
    0.27
    ier
    0.27
    Activations Density 0.022%

    No Known Activations