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. 71288
    Prev
    Next
    INDEX
    Explanations

    engineering or scientific research

    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
     outFile
    -0.08
    Y
    -0.07
    pictureBox
    -0.07
     spawning
    -0.07
    バイ
    -0.07
    Ele
    -0.07
     Exactly
    -0.07
    =`
    -0.07
    (separator
    -0.07
    callee
    -0.06
    POSITIVE LOGITS
    采摘
    0.07
    IFA
    0.07
     isl
    0.07
    -sign
    0.07
    -send
    0.07
    砀
    0.07
    _core
    0.07
    Lane
    0.06
    ctor
    0.06
    찿
    0.06
    Activations Density 0.120%

    No Known Activations