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. 71428
    Prev
    Next
    INDEX
    Explanations

    Ripple

    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
     Blu
    -0.07
     dash
    -0.07
     Öz
    -0.07
    ánd
    -0.07
     denominator
    -0.07
     분
    -0.07
     blows
    -0.07
    уб
    -0.07
    jav
    -0.07
     horn
    -0.07
    POSITIVE LOGITS
     fisheries
    0.08
     einf
    0.07
    .getClient
    0.07
    .just
    0.07
     recher
    0.07
     entreg
    0.07
     hover
    0.06
    �
    0.06
    ทำการ
    0.06
    _calendar
    0.06
    Activations Density 0.001%

    No Known Activations