© 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. 14-TRANSCODER-HP
    7. 41245
    Prev
    Next
    INDEX
    Explanations

    licenses and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĢĥ
    -0.30
    ption
    -0.27
    cling
    -0.27
     bezpieczeÅĦstwa
    -0.26
    oding
    -0.26
    弦
    -0.26
    ewood
    -0.25
    翳
    -0.24
    åħ¨éĿ¢åıijå±ķ
    -0.24
     mum
    -0.24
    POSITIVE LOGITS
    dao
    0.26
    uids
    0.26
    .NewRequest
    0.26
    .isValid
    0.25
     Pork
    0.25
    è¹ī
    0.25
    AME
    0.24
     involving
    0.24
    éħª
    0.24
    Advisor
    0.24
    Activations Density 0.121%

    No Known Activations