Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 72621
    Prev
    Next
    INDEX
    Explanations

    statements/uncertainties

    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
    juan
    -0.07
    脂
    -0.07
    must
    -0.07
     loc
    -0.07
                             ↵
    -0.06
    [position
    -0.06
    opot
    -0.06
    ellido
    -0.06
    شك
    -0.06
     굉
    -0.06
    POSITIVE LOGITS
    ')}</
    0.07
    𝗘
    0.07
    страива
    0.07
    追溯
    0.06
    _expected
    0.06
    _Column
    0.06
    '],['
    0.06
    主业
    0.06
     Compensation
    0.06
    必将
    0.06
    Activations Density 0.000%

    No Known Activations