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. 88306
    Prev
    Next
    INDEX
    Explanations

    news articles

    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
    ⛇
    -0.08
     トラック
    -0.07
     mutations
    -0.07
     fidelity
    -0.07
    Ju
    -0.07
    チュ
    -0.07
     specular
    -0.07
     Güncelle
    -0.07
     sift
    -0.07
    فائ
    -0.07
    POSITIVE LOGITS
    allee
    0.07
    波动
    0.07
    }});↵
    0.07
     str
    0.07
     ""));↵
    0.06
    ds
    0.06
     };↵
    0.06
    Clearly
    0.06
    rolled
    0.06
    '});↵
    0.06
    Activations Density 0.006%

    No Known Activations