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. 44144
    Prev
    Next
    INDEX
    Explanations

    Technical/formal topics

    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
    "+
    -0.08
     '}';↵
    -0.07
     kneeling
    -0.07
     Norwich
    -0.07
    _syntax
    -0.07
    .rel
    -0.07
     Savage
    -0.07
    蕻
    -0.07
    -factor
    -0.07
    华南
    -0.07
    POSITIVE LOGITS
    �
    0.07
    本基金
    0.07
    iff
    0.07
     rects
    0.07
     없다
    0.07
    \Bundle
    0.07
    卺
    0.07
    明らか
    0.07
    Embed
    0.07
     BIT
    0.06
    Activations Density 0.169%

    No Known Activations