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. 88247
    Prev
    Next
    INDEX
    Explanations

    aging

    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
    畢
    -0.07
    życz
    -0.07
    當您
    -0.07
     dripping
    -0.07
     delighted
    -0.07
    格外
    -0.07
    您同意
    -0.07
     sighed
    -0.06
    诏
    -0.06
     ecstatic
    -0.06
    POSITIVE LOGITS
     zun
    0.07
    出现了
    0.07
    进行了
    0.07
     UIS
    0.07
    _lab
    0.07
     Vor
    0.07
    等诸多
    0.07
    _LANG
    0.06
    RARY
    0.06
    сел
    0.06
    Activations Density 0.033%

    No Known Activations