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. 24711
    Prev
    Next
    INDEX
    Explanations

    Court

    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
     envi
    -0.07
     crear
    -0.07
     pillow
    -0.07
    -pencil
    -0.07
    -fired
    -0.07
    相同
    -0.06
     telesc
    -0.06
    three
    -0.06
    eph
    -0.06
    透露
    -0.06
    POSITIVE LOGITS
    	FOR
    0.08
    经济增长
    0.08
     withholding
    0.07
    无缘
    0.07
    ಶ
    0.07
     Lak
    0.07
     Dota
    0.07
     austerity
    0.07
    风控
    0.07
    .statusText
    0.07
    Activations Density 0.000%

    No Known Activations