© 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. 23-TRANSCODER-HP
    7. 24275
    Prev
    Next
    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PERT
    -0.27
    inputEmail
    -0.26
     impressed
    -0.25
    adoo
    -0.25
     Amit
    -0.24
     Smarty
    -0.24
    论
    -0.24
     mdb
    -0.24
    eva
    -0.24
     preempt
    -0.24
    POSITIVE LOGITS
    ä¸Ģç¯ĩ
    0.27
    åıijå±ķéĺ¶æ®µ
    0.26
    orst
    0.26
    æķ´
    0.25
    ä¸Ģåľº
    0.25
     deriving
    0.25
    iores
    0.25
    æĿ¿
    0.24
    (ActionEvent
    0.24
    çĪĨçĤ¸
    0.24
    Activations Density 0.001%

    No Known Activations