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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 46552
    Prev
    Next
    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ול
    -0.08
    颈部
    -0.08
    若
    -0.08
     +=↵
    -0.07
    ODE
    -0.07
    Gb
    -0.07
    =↵
    -0.07
    信念
    -0.07
    odule
    -0.07
    ﲒ
    -0.07
    POSITIVE LOGITS
     jdbc
    0.08
     مش
    0.07
     Mend
    0.07
     הי
    0.07
     المو
    0.07
    	mv
    0.07
    .awtextra
    0.07
     mappedBy
    0.07
     peny
    0.07
    环境保护
    0.07
    Activations Density 0.010%

    No Known Activations