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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 35732
    Prev
    Next
    INDEX
    Explanations

    Software commits and versions

    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
     prenatal
    -0.07
     Lisa
    -0.07
    rząd
    -0.07
     hồ
    -0.07
    jom
    -0.07
    しておく
    -0.06
     hav
    -0.06
     dispar
    -0.06
     Ev
    -0.06
     seemed
    -0.06
    POSITIVE LOGITS
    折
    0.07
     targeting
    0.06
    sequences
    0.06
    (arc
    0.06
    ArrayType
    0.06
     Bücher
    0.06
    瑭
    0.06
    /con
    0.06
     Ergebn
    0.06
    	mock
    0.06
    Activations Density 0.007%

    No Known Activations