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. 36168
    Prev
    Next
    INDEX
    Explanations

    (

    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
     Nim
    -0.07
    ianne
    -0.07
    Cog
    -0.07
     NIR
    -0.07
     goat
    -0.07
     Pet
    -0.06
    dispose
    -0.06
    шив
    -0.06
    亸
    -0.06
     residents
    -0.06
    POSITIVE LOGITS
    proxy
    0.07
     letras
    0.07
    errorMsg
    0.07
    ('\\
    0.07
    verification
    0.07
     Ankara
    0.07
    ('&
    0.07
    (EC
    0.07
    ,value
    0.07
     случай
    0.07
    Activations Density 0.049%

    No Known Activations