© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 86128
    Prev
    Next
    INDEX
    Explanations

    addObserver

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Edgar
    -0.08
     yt
    -0.07
    堆积
    -0.06
     nga
    -0.06
     allot
    -0.06
    utra
    -0.06
     archives
    -0.06
     Andre
    -0.06
     Adapter
    -0.06
    并不多
    -0.06
    POSITIVE LOGITS
     reporters
    0.08
    .reason
    0.07
    (Math
    0.07
     dancers
    0.07
    зад
    0.07
    ([]
    0.07
     FOOT
    0.07
    izabeth
    0.07
    /welcome
    0.07
    Lo
    0.07
    Activations Density 0.006%

    No Known Activations