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

    Neuronpedia

    APICircuit 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. 43838
    Prev
    Next
    INDEX
    Explanations

    License

    np_max-act-logits · gemini-2.0-flash
    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
     queue
    -0.07
    一些
    -0.07
    𬒗
    -0.07
    注意到
    -0.07
    考虑到
    -0.07
    人才培养
    -0.07
    her
    -0.07
    一族
    -0.07
    \":
    -0.07
     places
    -0.07
    POSITIVE LOGITS
    ﭩ
    0.08
     Depot
    0.07
    艎
    0.07
    Բ
    0.07
     sucht
    0.07
     świad
    0.07
    urrets
    0.07
    FFFF
    0.07
     đự
    0.07
    specs
    0.07
    Activations Density 0.003%

    No Known Activations