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. 72536
    Prev
    Next
    INDEX
    Explanations

    ask

    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
    _gp
    -0.07
    eof
    -0.07
     earthqu
    -0.07
    aphael
    -0.07
    -message
    -0.07
     epoch
    -0.07
     rightly
    -0.07
     początku
    -0.07
     ',
    -0.07
    نطق
    -0.07
    POSITIVE LOGITS
    umerator
    0.07
    互
    0.07
    Numer
    0.06
     syncing
    0.06
    DEN
    0.06
    �
    0.06
    カ
    0.06
    Kind
    0.06
     prot
    0.06
     prospect
    0.06
    Activations Density 0.139%

    No Known Activations