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. 129571
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    下发
    -0.07
     pigment
    -0.07
     heroin
    -0.07
     buurt
    -0.07
    Liver
    -0.07
     nível
    -0.07
    _employee
    -0.07
    舒服
    -0.07
    活性
    -0.06
    ڸ
    -0.06
    POSITIVE LOGITS
    override
    0.07
    应当
    0.07
    十四
    0.07
    /modal
    0.07
    ин
    0.07
    :url
    0.06
    تضمن
    0.06
    ented
    0.06
    .Zoom
    0.06
    ▦
    0.06
    Activations Density 0.008%

    No Known Activations