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. 88077
    Prev
    Next
    INDEX
    Explanations

    inner

    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
     stockholm
    -0.08
     형
    -0.07
    (track
    -0.07
    orgetown
    -0.07
    皇马
    -0.07
     automobiles
    -0.07
    Aud
    -0.07
     школ
    -0.07
     offsetX
    -0.07
    mpz
    -0.07
    POSITIVE LOGITS
    	continue
    0.07
    (g
    0.07
    楼层
    0.06
     agents
    0.06
    ﭯ
    0.06
     deb
    0.06
     وهذا
    0.06
    缺
    0.06
    批准
    0.06
    嗌
    0.06
    Activations Density 0.018%

    No Known Activations