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. 15-RESID-POST-AA
    6. 13719
    Prev
    Next
    INDEX
    Explanations

    diagnosis/admission

    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
    껴
    -0.06
    Ross
    -0.06
     reset
    -0.06
     frosting
    -0.06
    יפות
    -0.06
    فضل
    -0.06
     חברות
    -0.06
     thuận
    -0.06
    햬
    -0.06
    _android
    -0.06
    POSITIVE LOGITS
     elev
    0.09
    轻易
    0.08
     Customer
    0.07
    eliness
    0.07
    Ơ
    0.07
     Registers
    0.07
     infringement
    0.07
    aN
    0.07
    ransition
    0.07
    楫
    0.07
    Activations Density 0.020%

    No Known Activations