© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 59553
    Prev
    Next
    INDEX
    Explanations

    Google algorithm updates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.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
    Ƞ
    -0.07
    씩
    -0.07
     댓글
    -0.07
    מטוס
    -0.07
    ㅅ
    -0.06
     import
    -0.06
     конт
    -0.06
    infra
    -0.06
    Courtesy
    -0.06
    POSITIVE LOGITS
     Plaza
    0.07
    "is
    0.07
     trilogy
    0.07
     Haven
    0.07
     Почему
    0.07
    too
    0.07
     TU
    0.07
    .Names
    0.06
     모
    0.06
     Io
    0.06
    Activations Density 0.039%

    No Known Activations