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. 109952
    Prev
    Next
    INDEX
    Explanations

    exclamation points

    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
    四肢
    -0.07
    不锈
    -0.07
    _setopt
    -0.07
    钿
    -0.07
    specific
    -0.07
     transplant
    -0.06
    瞽
    -0.06
     التابعة
    -0.06
     TestBed
    -0.06
    颗
    -0.06
    POSITIVE LOGITS
     sliding
    0.08
    感谢
    0.07
     Heating
    0.07
     diff
    0.07
    ありました
    0.07
     Shooting
    0.07
    Month
    0.06
     marsh
    0.06
    上升
    0.06
    战胜
    0.06
    Activations Density 0.029%

    No Known Activations