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. 36055
    Prev
    Next
    INDEX
    Explanations

    drug distribution legal code

    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
    -month
    -0.07
    不仅可以
    -0.06
    女士
    -0.06
    eyond
    -0.06
     Hãy
    -0.06
    (source
    -0.06
     Cette
    -0.06
    ことが
    -0.06
    劳动者
    -0.06
     hym
    -0.06
    POSITIVE LOGITS
    omin
    0.08
    就被
    0.07
    جمال
    0.07
     Sahara
    0.07
    枸杞
    0.07
    _Event
    0.07
    QUERY
    0.07
    燃煤
    0.06
    :no
    0.06
    iasco
    0.06
    Activations Density 0.008%

    No Known Activations