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. 2412
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    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
     eo
    -0.07
     illumination
    -0.07
    ']
    ↵
    ↵
    -0.07
     erb
    -0.06
     даже
    -0.06
     '/'↵
    -0.06
    .")↵↵
    -0.06
    ...")↵
    -0.06
    ivr
    -0.06
    Follow
    -0.06
    POSITIVE LOGITS
    living
    0.07
    ᑭ
    0.07
     reins
    0.07
    爸爸
    0.07
     PKK
    0.07
     QSize
    0.07
    掮
    0.07
    反映
    0.07
     ResultSet
    0.06
    _Request
    0.06
    Activations Density 0.008%

    No Known Activations