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. 59717
    Prev
    Next
    INDEX
    Explanations

    resistant

    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
    ǎ
    -0.09
    菪
    -0.07
    ︽
    -0.07
     PodsDummy
    -0.07
    龉
    -0.07
     pardon
    -0.07
    .tv
    -0.07
    ܀
    -0.07
    箓
    -0.07
     Synopsis
    -0.07
    POSITIVE LOGITS
     *,
    0.09
    DAT
    0.07
     &,
    0.07
     "↵
    0.07
    arga
    0.07
    */,
    0.07
    _ENTITY
    0.07
    %.
    0.07
    分割
    0.07
     navigationController
    0.07
    Activations Density 0.009%

    No Known Activations