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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 71249
    Prev
    Next
    INDEX
    Explanations

    programming languages

    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
     unlike
    -0.07
    (instance
    -0.07
     getTitle
    -0.07
    (Print
    -0.07
    十六
    -0.07
     ves
    -0.07
     Soviets
    -0.07
    _Edit
    -0.07
     Пред
    -0.07
     EXPORT
    -0.06
    POSITIVE LOGITS
    .nick
    0.08
    logout
    0.07
    räg
    0.07
    habit
    0.07
    馘
    0.07
     الديمقرا
    0.07
    �
    0.07
    맺
    0.06
    ToBounds
    0.06
    orny
    0.06
    Activations Density 0.137%

    No Known Activations