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. 36437
    Prev
    Next
    INDEX
    Explanations

    Before

    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
     itemType
    -0.08
    _lstm
    -0.07
    (ti
    -0.07
     Atkins
    -0.07
    热度
    -0.06
    Vertex
    -0.06
    apters
    -0.06
     enthusiastically
    -0.06
     indis
    -0.06
     Singer
    -0.06
    POSITIVE LOGITS
     Nou
    0.07
    rew
    0.07
    隶属
    0.07
    руг
    0.06
     centre
    0.06
    יופי
    0.06
    还可以
    0.06
    -history
    0.06
     ob
    0.06
     presentation
    0.06
    Activations Density 0.002%

    No Known Activations