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. 2924
    Prev
    Next
    INDEX
    Explanations

    Code and documentation

    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
    人事
    -0.08
    [string
    -0.08
    (Boolean
    -0.07
     abc
    -0.07
     memb
    -0.07
    システ
    -0.07
    主观
    -0.07
    .xlabel
    -0.07
    .parts
    -0.06
     faults
    -0.06
    POSITIVE LOGITS
    ungeon
    0.08
    Michelle
    0.07
    Strength
    0.07
     monoc
    0.07
     gé
    0.06
    ировки
    0.06
    /gui
    0.06
     construção
    0.06
    larınız
    0.06
    )<
    0.06
    Activations Density 0.002%

    No Known Activations