Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 130943
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    有多么
    -0.08
     fasc
    -0.07
    ITS
    -0.07
     thereof
    -0.07
     AVG
    -0.07
    emax
    -0.07
    ates
    -0.06
    听众
    -0.06
    有多
    -0.06
    exp
    -0.06
    POSITIVE LOGITS
     Nina
    0.07
     Trail
    0.07
    Fire
    0.07
    縣
    0.06
    uggy
    0.06
     emulator
    0.06
    Directory
    0.06
    秦皇岛
    0.06
    铁路
    0.06
    Fair
    0.06
    Activations Density 0.000%

    No Known Activations