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. 7119
    Prev
    Next
    INDEX
    Explanations

    terms of service changes

    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
    Mail
    -0.07
    .visit
    -0.07
    ("{
    -0.07
    =""/>↵
    -0.07
     visiting
    -0.07
    ço
    -0.06
    敫
    -0.06
     rendition
    -0.06
     Finnish
    -0.06
    <Key
    -0.06
    POSITIVE LOGITS
    龍
    0.08
     realities
    0.08
    طرح
    0.07
    科学家
    0.07
     тем
    0.07
    oron
    0.07
     wound
    0.07
    plx
    0.07
    стер
    0.07
    سطح
    0.07
    Activations Density 0.002%

    No Known Activations