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. 129106
    Prev
    Next
    INDEX
    Explanations

    that this

    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
    -read
    -0.07
    łem
    -0.07
    还是比较
    -0.07
    declaration
    -0.06
    懊
    -0.06
    by
    -0.06
     DataContext
    -0.06
    箩
    -0.06
    _RESOURCE
    -0.06
     Kann
    -0.06
    POSITIVE LOGITS
    集装
    0.07
     cảnh
    0.07
    [float
    0.07
    警
    0.07
    进口
    0.07
    琚
    0.07
    أمر
    0.06
     hinge
    0.06
     condu
    0.06
     فعل
    0.06
    Activations Density 0.110%

    No Known Activations