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. 71219
    Prev
    Next
    INDEX
    Explanations

    numbers and equations

    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
    bundles
    -0.07
    istor
    -0.07
    ceptar
    -0.07
    _batches
    -0.07
     Sciences
    -0.07
    生物学
    -0.07
    URING
    -0.07
    Radians
    -0.07
    raphics
    -0.07
     Monad
    -0.06
    POSITIVE LOGITS
    一事
    0.07
    下一代
    0.07
    油价
    0.07
    ość
    0.06
    ('--
    0.06
    小狗
    0.06
    船上
    0.06
    HAL
    0.06
    的身份
    0.06
    卻
    0.06
    Activations Density 0.016%

    No Known Activations